Understanding Addition in Transformers
This provides incremental insights into Transformer interpretability for researchers, focusing on a specific arithmetic task.
The paper analyzes how a one-layer Transformer model performs n-digit integer addition, finding it uses parallel digit streams with position-specific algorithms and identifies a high-loss edge case.
Understanding the inner workings of machine learning models like Transformers is vital for their safe and ethical use. This paper provides a comprehensive analysis of a one-layer Transformer model trained to perform n-digit integer addition. Our findings suggest that the model dissects the task into parallel streams dedicated to individual digits, employing varied algorithms tailored to different positions within the digits. Furthermore, we identify a rare scenario characterized by high loss, which we explain. By thoroughly elucidating the model's algorithm, we provide new insights into its functioning. These findings are validated through rigorous testing and mathematical modeling, thereby contributing to the broader fields of model understanding and interpretability. Our approach opens the door for analyzing more complex tasks and multi-layer Transformer models.