Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1784 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.5431. Min Act: -0.1700
Data Index: 466409 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.5118. Min Act: -0.1700
Data Index: 7324405 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.4493. Min Act: -0.1700
Data Index: 1279959 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.3556. Min Act: -0.1700
Data Index: 6077141 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.3556. Min Act: -0.1700
Data Index: 4899984 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.3556. Min Act: -0.1700
Data Index: 2345375 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.3243. Min Act: -0.1700
Data Index: 3259476 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.3243. Min Act: -0.1700
Data Index: 3589739 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.2618. Min Act: -0.1700
Data Index: 217977 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.2618. Min Act: -0.1700
Data Index: 4955007 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.2306. Min Act: -0.1700
Data Index: 215211 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.2306. Min Act: -0.1700
Data Index: 8384169 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.2306. Min Act: -0.1700
Data Index: 3195589 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.2618. Min Act: -0.1700
Data Index: 7131997 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.2306. Min Act: -0.1700
Data Index: 4307827 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.1681. Min Act: -0.1700
Data Index: 6973756 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.1993. Min Act: -0.1700
Data Index: 6715527 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.1681. Min Act: -0.1700
Data Index: 5200014 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.1368. Min Act: -0.1700
Data Index: 5529518 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5431. Min Range: -5.5431
Max Act: 5.1056. Min Act: -0.1700
Data Index: 1792584 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19