Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.6851. Min Act: -0.1700
Data Index: 4180474 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.6226. Min Act: -0.1700
Data Index: 3209982 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.4664. Min Act: -0.1700
Data Index: 8199715 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.4351. Min Act: -0.1700
Data Index: 7317190 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.4039. Min Act: -0.1700
Data Index: 19964 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.4039. Min Act: -0.1603
Data Index: 6899396 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.3726. Min Act: -0.1700
Data Index: 1419925 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.3726. Min Act: -0.1699
Data Index: 6734799 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.3414. Min Act: -0.1700
Data Index: 6468335 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.3101. Min Act: -0.1700
Data Index: 6399625 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.2789. Min Act: -0.1700
Data Index: 2335539 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.2789. Min Act: -0.1700
Data Index: 6399620 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.2789. Min Act: -0.1700
Data Index: 6893711 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.2476. Min Act: -0.1700
Data Index: 6895440 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.2476. Min Act: -0.1700
Data Index: 3209983 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.2476. Min Act: -0.1700
Data Index: 5031522 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.2164. Min Act: -0.1700
Data Index: 6605391 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.2164. Min Act: -0.1700
Data Index: 3143255 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.2164. Min Act: -0.1700
Data Index: 19969 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6851. Min Range: -4.6851
Max Act: 4.1851. Min Act: -0.1700
Data Index: 2335545 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19