Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 426 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0355. Min Range: -6.0355
Max Act: 6.0042. Min Act: -0.1700
Data Index: 1913637 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0355. Min Range: -6.0355
Max Act: 6.0355. Min Act: -0.1700
Data Index: 4557160 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0355. Min Range: -6.0355
Max Act: 6.0042. Min Act: -0.1700
Data Index: 865928 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.9417. Min Act: -0.1700
Data Index: 7103109 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.9417. Min Act: -0.1700
Data Index: 5895815 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.8792. Min Act: -0.1700
Data Index: 7668015 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.9417. Min Act: -0.1700
Data Index: 6659771 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.8167. Min Act: -0.1700
Data Index: 7353065 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.8167. Min Act: -0.1700
Data Index: 6088815 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.8480. Min Act: -0.1700
Data Index: 5235365 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.7855. Min Act: -0.1700
Data Index: 228919 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.8167. Min Act: -0.1700
Data Index: 5984293 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.7542. Min Act: -0.1700
Data Index: 7018349 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.7542. Min Act: -0.1700
Data Index: 5188834 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.7855. Min Act: -0.1700
Data Index: 8738638 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.7855. Min Act: -0.1700
Data Index: 4508939 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.7542. Min Act: -0.1700
Data Index: 507422 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.7855. Min Act: -0.1700
Data Index: 600607 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.7542. Min Act: -0.1700
Data Index: 6948573 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0355. Min Range: -6.0355
Max Act: 5.7542. Min Act: -0.1700
Data Index: 7086870 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19