Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4474 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.7959. Min Act: -0.1700
Data Index: 2260465 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.5459. Min Act: -0.1700
Data Index: 5059574 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.4834. Min Act: -0.1700
Data Index: 4739342 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.4834. Min Act: -0.1700
Data Index: 1655677 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.4209. Min Act: -0.1700
Data Index: 2780728 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.2334. Min Act: -0.1700
Data Index: 2418747 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.2334. Min Act: -0.1700
Data Index: 4827310 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.1709. Min Act: -0.1700
Data Index: 7325717 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.1084. Min Act: -0.1700
Data Index: 7717418 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7959. Min Range: -12.7959
Max Act: 11.9834. Min Act: -0.1700
Data Index: 7368984 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.0459. Min Act: -0.1700
Data Index: 958119 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7959. Min Range: -12.7959
Max Act: 12.0459. Min Act: -0.1700
Data Index: 3217422 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7959. Min Range: -12.7959
Max Act: 11.9834. Min Act: -0.1700
Data Index: 2877459 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7959. Min Range: -12.7959
Max Act: 11.9209. Min Act: -0.1700
Data Index: 5914529 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7959. Min Range: -12.7959
Max Act: 11.9209. Min Act: -0.1700
Data Index: 3710280 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7959. Min Range: -12.7959
Max Act: 11.8584. Min Act: -0.1700
Data Index: 5984365 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7959. Min Range: -12.7959
Max Act: 11.7959. Min Act: -0.1700
Data Index: 1595519 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7959. Min Range: -12.7959
Max Act: 11.7959. Min Act: -0.1700
Data Index: 8166187 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7959. Min Range: -12.7959
Max Act: 11.7334. Min Act: -0.1700
Data Index: 4342955 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7959. Min Range: -12.7959
Max Act: 11.7334. Min Act: -0.1700
Data Index: 4395540 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19