Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1334. Min Range: -6.1334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 2238426 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.9459. Min Act: -0.1700
Data Index: 4370065 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.9147. Min Act: -0.1700
Data Index: 3199720 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.8522. Min Act: -0.1700
Data Index: 1318175 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.8522. Min Act: -0.1700
Data Index: 4257108 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.8522. Min Act: -0.1700
Data Index: 4356418 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.8209. Min Act: -0.1700
Data Index: 6478558 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.7897. Min Act: -0.1700
Data Index: 1138182 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.7584. Min Act: -0.1700
Data Index: 3597388 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.7897. Min Act: -0.1700
Data Index: 6919638 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6959. Min Act: -0.1700
Data Index: 8351835 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6959. Min Act: -0.1700
Data Index: 8172815 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6959. Min Act: -0.1700
Data Index: 1653494 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6647. Min Act: -0.1700
Data Index: 8128107 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6334. Min Act: -0.1700
Data Index: 8751888 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6334. Min Act: -0.1700
Data Index: 8274384 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6334. Min Act: -0.1700
Data Index: 5850023 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6022. Min Act: -0.1700
Data Index: 6862288 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6022. Min Act: -0.1700
Data Index: 2813182 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1334. Min Range: -6.1334
Max Act: 5.6022. Min Act: -0.1700
Data Index: 4295937 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19