Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.9779. Min Act: -0.1700
Data Index: 3850668 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.9154. Min Act: -0.1700
Data Index: 2967725 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.8529. Min Act: -0.1700
Data Index: 2383805 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.6967. Min Act: -0.1700
Data Index: 6873226 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.6654. Min Act: -0.1700
Data Index: 2242653 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.5717. Min Act: -0.1700
Data Index: 5579523 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.5717. Min Act: -0.1700
Data Index: 2272057 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.5717. Min Act: -0.1700
Data Index: 5090102 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.6029. Min Act: -0.1700
Data Index: 2641115 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.5092. Min Act: -0.1700
Data Index: 349346 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.5404. Min Act: -0.1700
Data Index: 4047520 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.5092. Min Act: -0.1700
Data Index: 2947195 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.5092. Min Act: -0.1700
Data Index: 4300270 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.4779. Min Act: -0.1700
Data Index: 4171550 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.5092. Min Act: -0.1700
Data Index: 881999 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.4467. Min Act: -0.1700
Data Index: 3770344 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.4467. Min Act: -0.1700
Data Index: 8434037 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.4779. Min Act: -0.1700
Data Index: 3564967 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.4467. Min Act: -0.1700
Data Index: 5963405 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9779. Min Range: -6.9779
Max Act: 6.4467. Min Act: -0.1700
Data Index: 6842940 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19