Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 885 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.5130. Min Act: -0.1700
Data Index: 5629373 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.4193. Min Act: -0.1700
Data Index: 4452513 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3880. Min Act: -0.1700
Data Index: 6492659 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3880. Min Act: -0.1700
Data Index: 1004175 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3568. Min Act: -0.1700
Data Index: 2504803 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 5607534 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2943. Min Act: -0.1700
Data Index: 5789382 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 4393144 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 822903 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2318. Min Act: -0.1700
Data Index: 7279034 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2318. Min Act: -0.1700
Data Index: 5195904 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2318. Min Act: -0.1700
Data Index: 4741192 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2318. Min Act: -0.1700
Data Index: 3743497 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 5195901 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2318. Min Act: -0.1700
Data Index: 691314 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2005. Min Act: -0.1700
Data Index: 7409364 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2005. Min Act: -0.1700
Data Index: 4981901 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2005. Min Act: -0.1700
Data Index: 3972906 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1693. Min Act: -0.1700
Data Index: 691313 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1693. Min Act: -0.1700
Data Index: 5629372 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19