Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4646 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.5661. Min Act: -0.1700
Data Index: 2040441 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.3473. Min Act: -0.1700
Data Index: 105362 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.3161. Min Act: -0.1700
Data Index: 5405829 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.3161. Min Act: -0.1700
Data Index: 7082966 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.3161. Min Act: -0.1699
Data Index: 8565917 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2536. Min Act: -0.1700
Data Index: 4529989 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2848. Min Act: -0.1700
Data Index: 5631866 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2848. Min Act: -0.1700
Data Index: 2768404 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2536. Min Act: -0.1700
Data Index: 5130481 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2848. Min Act: -0.1700
Data Index: 7250843 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2848. Min Act: -0.1700
Data Index: 3383940 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2848. Min Act: -0.1700
Data Index: 135819 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2536. Min Act: -0.1700
Data Index: 180855 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2536. Min Act: -0.1700
Data Index: 1253563 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2848. Min Act: -0.1700
Data Index: 3890978 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2536. Min Act: -0.1700
Data Index: 8213375 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2536. Min Act: -0.1700
Data Index: 8263672 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2536. Min Act: -0.1700
Data Index: 2544544 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2223. Min Act: -0.1700
Data Index: 7786010 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5661. Min Range: -5.5661
Max Act: 5.2223. Min Act: -0.1700
Data Index: 3693833 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19