On Functional Activations in Deep Neural Networks
This work addresses the opacity of deep neural networks for researchers and practitioners by providing a method to understand model workings, though it is incremental as it adapts existing techniques to AI.
The study applied functional neuroimaging techniques to the Facebook Galactica-125M language model to probe its internal functional structure, identifying distinct, overlapping networks for tasks like medical imaging and pathology that were repeatable and could accurately identify tasks.
Background: Deep neural networks have proven to be powerful computational tools for modeling, prediction, and generation. However, the workings of these models have generally been opaque. Recent work has shown that the performance of some models are modulated by overlapping functional networks of connections within the models. Here the techniques of functional neuroimaging are applied to an exemplary large language model to probe its functional structure. Methods: A series of block-designed task-based prompt sequences were generated to probe the Facebook Galactica-125M model. Tasks included prompts relating to political science, medical imaging, paleontology, archeology, pathology, and random strings presented in an off/on/off pattern with prompts about other random topics. For the generation of each output token, all layer output values were saved to create an effective time series. General linear models were fit to the data to identify layer output values which were active with the tasks. Results: Distinct, overlapping networks were identified with each task. Most overlap was observed between medical imaging and pathology networks. These networks were repeatable across repeated performance of related tasks, and correspondence of identified functional networks and activation in tasks not used to define the functional networks was shown to accurately identify the presented task. Conclusion: The techniques of functional neuroimaging can be applied to deep neural networks as a means to probe their workings. Identified functional networks hold the potential for use in model alignment, modulation of model output, and identifying weights to target in fine-tuning.