Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9942. Min Act: -0.1700
Data Index: 5445890 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9630. Min Act: -0.1700
Data Index: 6285493 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9630. Min Act: -0.1700
Data Index: 5321137 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9317. Min Act: -0.1700
Data Index: 7095946 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9630. Min Act: -0.1700
Data Index: 5536684 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9004. Min Act: -0.1700
Data Index: 7942172 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9004. Min Act: -0.1700
Data Index: 662313 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9317. Min Act: -0.1700
Data Index: 3020241 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9004. Min Act: -0.1700
Data Index: 4024583 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9004. Min Act: -0.1700
Data Index: 2530427 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9004. Min Act: -0.1700
Data Index: 5182867 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9004. Min Act: -0.1700
Data Index: 165156 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9004. Min Act: -0.1700
Data Index: 8054571 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.8692. Min Act: -0.1700
Data Index: 4010975 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.8692. Min Act: -0.1700
Data Index: 477947 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9004. Min Act: -0.1700
Data Index: 6061415 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.9004. Min Act: -0.1700
Data Index: 1512749 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.8692. Min Act: -0.1700
Data Index: 1610754 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.8692. Min Act: -0.1700
Data Index: 4024587 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9942. Min Range: -3.9942
Max Act: 3.8692. Min Act: -0.1700
Data Index: 6304109 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19