Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4239 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1334. Min Range: -7.1334
Max Act: 7.1334. Min Act: -0.1700
Data Index: 4518501 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.3834. Min Act: -0.1700
Data Index: 7371823 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.3834. Min Act: -0.1700
Data Index: 3386494 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.3521. Min Act: -0.1700
Data Index: 1302405 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.3521. Min Act: -0.1700
Data Index: 6481682 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.3209. Min Act: -0.1700
Data Index: 5152658 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.2271. Min Act: -0.1699
Data Index: 6938989 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.2584. Min Act: -0.1700
Data Index: 5929476 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.2271. Min Act: -0.1699
Data Index: 7414496 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.1959. Min Act: -0.1700
Data Index: 4956211 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.1646. Min Act: -0.1698
Data Index: 636550 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.1646. Min Act: -0.1700
Data Index: 3537076 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.1646. Min Act: -0.1700
Data Index: 3552206 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 646272 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 8416733 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 7772067 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.1334. Min Act: -0.1700
Data Index: 776785 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.1021. Min Act: -0.1700
Data Index: 3168538 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.0709. Min Act: -0.1700
Data Index: 2991334 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1334. Min Range: -7.1334
Max Act: 6.0709. Min Act: -0.1700
Data Index: 7135524 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19