Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.8011. Min Act: -0.1700
Data Index: 6654980 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.7698. Min Act: -0.1700
Data Index: 6066710 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.7386. Min Act: -0.1700
Data Index: 7837775 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.7073. Min Act: -0.1700
Data Index: 3260897 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.6136. Min Act: -0.1700
Data Index: 3965553 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.6448. Min Act: -0.1700
Data Index: 2141775 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5823. Min Act: -0.1700
Data Index: 3939130 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.6136. Min Act: -0.1700
Data Index: 1075419 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.6136. Min Act: -0.1700
Data Index: 5330457 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.6136. Min Act: -0.1700
Data Index: 5886119 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5823. Min Act: -0.1700
Data Index: 5680626 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5511. Min Act: -0.1700
Data Index: 5289053 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5823. Min Act: -0.1700
Data Index: 5627398 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5823. Min Act: -0.1700
Data Index: 8295499 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5511. Min Act: -0.1700
Data Index: 790843 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5511. Min Act: -0.1700
Data Index: 5855546 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5511. Min Act: -0.1700
Data Index: 2678521 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5511. Min Act: -0.1700
Data Index: 5230654 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5511. Min Act: -0.1700
Data Index: 6695733 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8011. Min Range: -6.8011
Max Act: 6.5511. Min Act: -0.1700
Data Index: 4388659 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19