Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5080 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.5029. Min Act: -0.1700
Data Index: 6783078 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.5029. Min Act: -0.1700
Data Index: 6227695 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.4717. Min Act: -0.1700
Data Index: 6248367 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.4092. Min Act: -0.1700
Data Index: 3774302 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.3467. Min Act: -0.1700
Data Index: 2457582 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.3467. Min Act: -0.1700
Data Index: 7774606 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.3467. Min Act: -0.1700
Data Index: 7434953 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.3779. Min Act: -0.1700
Data Index: 6493627 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.3467. Min Act: -0.1700
Data Index: 3774675 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2842. Min Act: -0.1700
Data Index: 5980712 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2842. Min Act: -0.1700
Data Index: 6229230 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2842. Min Act: -0.1700
Data Index: 8195927 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2842. Min Act: -0.1700
Data Index: 2502910 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2529. Min Act: -0.1700
Data Index: 1460338 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2529. Min Act: -0.1700
Data Index: 234891 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2529. Min Act: -0.1700
Data Index: 1517206 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2217. Min Act: -0.1700
Data Index: 6590208 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2217. Min Act: -0.1700
Data Index: 6258139 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2217. Min Act: -0.1700
Data Index: 3319412 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5029. Min Range: -5.5029
Max Act: 5.2529. Min Act: -0.1700
Data Index: 2873701 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19