Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5855 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.1334. Min Act: -0.1700
Data Index: 5967114 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.1022. Min Act: -0.1700
Data Index: 6319738 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.1022. Min Act: -0.1700
Data Index: 4518817 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.1334. Min Act: -0.1700
Data Index: 8626621 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.1022. Min Act: -0.1700
Data Index: 1296314 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.0397. Min Act: -0.1700
Data Index: 8008788 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.0397. Min Act: -0.1700
Data Index: 2948675 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.0397. Min Act: -0.1700
Data Index: 2670119 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.0397. Min Act: -0.1700
Data Index: 673808 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.0397. Min Act: -0.1700
Data Index: 8698060 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1334. Min Range: -4.1334
Max Act: 4.0397. Min Act: -0.1700
Data Index: 1048623 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1334. Min Range: -4.1334
Max Act: 3.9771. Min Act: -0.1700
Data Index: 8662364 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1334. Min Range: -4.1334
Max Act: 3.9771. Min Act: -0.1700
Data Index: 744781 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1334. Min Range: -4.1334
Max Act: 3.9771. Min Act: -0.1700
Data Index: 6891913 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1334. Min Range: -4.1334
Max Act: 3.9771. Min Act: -0.1700
Data Index: 3962669 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1334. Min Range: -4.1334
Max Act: 3.9771. Min Act: -0.1700
Data Index: 1259212 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1334. Min Range: -4.1334
Max Act: 3.9771. Min Act: -0.1700
Data Index: 7955204 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1334. Min Range: -4.1334
Max Act: 3.9459. Min Act: -0.1700
Data Index: 4983855 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1334. Min Range: -4.1334
Max Act: 3.9459. Min Act: -0.1700
Data Index: 8689468 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1334. Min Range: -4.1334
Max Act: 3.9459. Min Act: -0.1700
Data Index: 8801520 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19