Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.9848. Min Act: -0.1700
Data Index: 8369913 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.7973. Min Act: -0.1700
Data Index: 113851 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.7348. Min Act: -0.1700
Data Index: 3486555 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.7036. Min Act: -0.1700
Data Index: 4309158 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.7036. Min Act: -0.1700
Data Index: 4052609 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6723. Min Act: -0.1700
Data Index: 6460078 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6411. Min Act: -0.1700
Data Index: 2858546 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6411. Min Act: -0.1700
Data Index: 3103234 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6411. Min Act: -0.1700
Data Index: 627581 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6411. Min Act: -0.1700
Data Index: 536235 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6411. Min Act: -0.1700
Data Index: 8435445 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6411. Min Act: -0.1700
Data Index: 1180547 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6411. Min Act: -0.1700
Data Index: 3839414 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6098. Min Act: -0.1700
Data Index: 3283013 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6411. Min Act: -0.1700
Data Index: 2107674 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6098. Min Act: -0.1700
Data Index: 6250789 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.5786. Min Act: -0.1700
Data Index: 142678 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6098. Min Act: -0.1700
Data Index: 3279353 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6098. Min Act: -0.1700
Data Index: 2507993 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9848. Min Range: -4.9848
Max Act: 4.6098. Min Act: -0.1700
Data Index: 5156298 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19