Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.9301. Min Act: -0.1700
Data Index: 7817735 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.8363. Min Act: -0.1700
Data Index: 687987 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.8363. Min Act: -0.1700
Data Index: 2366862 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.7738. Min Act: -0.1700
Data Index: 1081449 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.7426. Min Act: -0.1700
Data Index: 643260 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.7738. Min Act: -0.1700
Data Index: 6700525 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.7426. Min Act: -0.1700
Data Index: 5178093 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.7113. Min Act: -0.1700
Data Index: 5557169 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.6801. Min Act: -0.1700
Data Index: 212344 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.6488. Min Act: -0.1700
Data Index: 4726931 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.6801. Min Act: -0.1700
Data Index: 5792870 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.6176. Min Act: -0.1700
Data Index: 1224556 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.5863. Min Act: -0.1700
Data Index: 6501555 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.6176. Min Act: -0.1700
Data Index: 961515 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.5863. Min Act: -0.1700
Data Index: 8727366 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.5863. Min Act: -0.1700
Data Index: 7865369 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.5551. Min Act: -0.1700
Data Index: 3461395 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.5551. Min Act: -0.1700
Data Index: 1720601 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.5551. Min Act: -0.1700
Data Index: 7550764 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9301. Min Range: -6.9301
Max Act: 6.5551. Min Act: -0.1700
Data Index: 7280326 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19