Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.5009. Min Act: -0.1700
Data Index: 4389229 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.4539. Min Act: -0.1700
Data Index: 5990608 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.4382. Min Act: -0.1700
Data Index: 5677297 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.4382. Min Act: -0.1700
Data Index: 5120582 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.4382. Min Act: -0.1700
Data Index: 1391416 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.3755. Min Act: -0.1700
Data Index: 60171 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.3598. Min Act: -0.1700
Data Index: 6856561 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.3441. Min Act: -0.1700
Data Index: 4443081 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.3127. Min Act: -0.1700
Data Index: 5913903 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.3127. Min Act: -0.1700
Data Index: 8656762 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2970. Min Act: -0.1700
Data Index: 6717964 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2813. Min Act: -0.1700
Data Index: 1444767 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2970. Min Act: -0.1700
Data Index: 7562746 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2813. Min Act: -0.1700
Data Index: 5291312 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2499. Min Act: -0.1700
Data Index: 1227468 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2499. Min Act: -0.1700
Data Index: 8140288 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2499. Min Act: -0.1700
Data Index: 4501942 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2499. Min Act: -0.1700
Data Index: 7826690 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2499. Min Act: -0.1700
Data Index: 7641273 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2499. Min Act: -0.1700
Data Index: 5762482 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19