Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.8757. Min Act: -0.1700
Data Index: 8222785 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.7507. Min Act: -0.1700
Data Index: 7141735 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.6570. Min Act: -0.1700
Data Index: 5957644 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.6257. Min Act: -0.1700
Data Index: 7218492 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.5945. Min Act: -0.1700
Data Index: 7373131 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.5007. Min Act: -0.1700
Data Index: 8011546 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.5007. Min Act: -0.1700
Data Index: 2551703 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.4695. Min Act: -0.1700
Data Index: 3536919 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3757. Min Act: -0.1700
Data Index: 7844264 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3757. Min Act: -0.1700
Data Index: 4843553 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3445. Min Act: -0.1700
Data Index: 1486868 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3132. Min Act: -0.1700
Data Index: 1002405 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3132. Min Act: -0.1700
Data Index: 5095852 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3132. Min Act: -0.1700
Data Index: 6038273 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3132. Min Act: -0.1700
Data Index: 8105696 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3132. Min Act: -0.1700
Data Index: 2533249 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3132. Min Act: -0.1700
Data Index: 3471218 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.3132. Min Act: -0.1700
Data Index: 4296035 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.2820. Min Act: -0.1700
Data Index: 6681956 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8757. Min Range: -7.8757
Max Act: 7.2507. Min Act: -0.1700
Data Index: 6827584 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19