Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0215. Min Range: -5.0215
Max Act: 5.0215. Min Act: -0.1700
Data Index: 4631027 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.9590. Min Act: -0.1700
Data Index: 949577 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.8340. Min Act: -0.1700
Data Index: 7822737 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.8027. Min Act: -0.1700
Data Index: 879320 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.7715. Min Act: -0.1700
Data Index: 8204855 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.7402. Min Act: -0.1700
Data Index: 6343136 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.7090. Min Act: -0.1700
Data Index: 6771935 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6777. Min Act: -0.1700
Data Index: 4888463 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6777. Min Act: -0.1700
Data Index: 3804942 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6777. Min Act: -0.1700
Data Index: 4913344 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6465. Min Act: -0.1700
Data Index: 3095574 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6465. Min Act: -0.1700
Data Index: 652589 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6152. Min Act: -0.1700
Data Index: 98117 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6465. Min Act: -0.1700
Data Index: 8095240 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6465. Min Act: -0.1700
Data Index: 279261 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6152. Min Act: -0.1700
Data Index: 1011369 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6465. Min Act: -0.1700
Data Index: 7438218 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6152. Min Act: -0.1700
Data Index: 7320910 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.6152. Min Act: -0.1700
Data Index: 5038655 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0215. Min Range: -5.0215
Max Act: 4.5840. Min Act: -0.1700
Data Index: 841547 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19