Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.4178. Min Act: -0.1700
Data Index: 8114966 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.3865. Min Act: -0.1700
Data Index: 8114967 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.2303. Min Act: -0.1700
Data Index: 6427098 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.1678. Min Act: -0.1700
Data Index: 4506626 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.1365. Min Act: -0.1700
Data Index: 1729629 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.1053. Min Act: -0.1700
Data Index: 3292976 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.0428. Min Act: -0.1700
Data Index: 6897484 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.0428. Min Act: -0.1700
Data Index: 46948 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.0428. Min Act: -0.1700
Data Index: 730317 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.0428. Min Act: -0.1700
Data Index: 5887623 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4178. Min Range: -6.4178
Max Act: 6.0115. Min Act: -0.1700
Data Index: 7944582 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4178. Min Range: -6.4178
Max Act: 5.9803. Min Act: -0.1700
Data Index: 7329663 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4178. Min Range: -6.4178
Max Act: 5.9803. Min Act: -0.1700
Data Index: 3685712 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4178. Min Range: -6.4178
Max Act: 5.9803. Min Act: -0.1700
Data Index: 1574248 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4178. Min Range: -6.4178
Max Act: 5.9803. Min Act: -0.1700
Data Index: 8011836 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4178. Min Range: -6.4178
Max Act: 5.9490. Min Act: -0.1700
Data Index: 1574249 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4178. Min Range: -6.4178
Max Act: 5.9490. Min Act: -0.1700
Data Index: 6001386 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4178. Min Range: -6.4178
Max Act: 5.9490. Min Act: -0.1700
Data Index: 3166131 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4178. Min Range: -6.4178
Max Act: 5.9490. Min Act: -0.1700
Data Index: 7729515 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4178. Min Range: -6.4178
Max Act: 5.9178. Min Act: -0.1700
Data Index: 3861849 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19