Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 341 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.5394. Min Act: -0.1700
Data Index: 1451540 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.4144. Min Act: -0.1700
Data Index: 7156923 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.3519. Min Act: -0.1700
Data Index: 5281610 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.2894. Min Act: -0.1700
Data Index: 5136856 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.2269. Min Act: -0.1700
Data Index: 3085497 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.2894. Min Act: -0.1700
Data Index: 3366575 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.2269. Min Act: -0.1700
Data Index: 2517490 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.2269. Min Act: -0.1700
Data Index: 4148030 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.1644. Min Act: -0.1700
Data Index: 628771 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.2269. Min Act: -0.1700
Data Index: 6066713 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.1019. Min Act: -0.1700
Data Index: 7530955 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.1644. Min Act: -0.1700
Data Index: 85023 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.1644. Min Act: -0.1700
Data Index: 2447562 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.0394. Min Act: -0.1700
Data Index: 2244279 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.0394. Min Act: -0.1700
Data Index: 1235931 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.0394. Min Act: -0.1700
Data Index: 3463937 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.0394. Min Act: -0.1700
Data Index: 2849907 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.0394. Min Act: -0.1700
Data Index: 5005074 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5394. Min Range: -10.5394
Max Act: 10.0394. Min Act: -0.1700
Data Index: 8602475 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5394. Min Range: -10.5394
Max Act: 9.9769. Min Act: -0.1700
Data Index: 6325550 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19