Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale

Understand

Language models have been shown to perform better with an increase in scale on a wide variety of tasks via the in-context learning paradigm.

• In this paper, we investigate the hypothesis that the ability of a large language model to in-context learn-perform a task is not uniformly spread across all of its underlying components.
• Using a 66 billion parameter language model (OPT-66B) across a diverse set of 14 downstream tasks, we find this is indeed the case: $\sim$70% of attention heads and $\sim$20% of feed forward networks can be removed with minimal decline in task performance.
• We find substantial overlap in the set of attention heads (un)important for in-context learning across tasks and number of in-context examples.