Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.9165. Min Act: -0.1700
Data Index: 3393045 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.7290. Min Act: -0.1700
Data Index: 5426753 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.6665. Min Act: -0.1700
Data Index: 3452204 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.6040. Min Act: -0.1700
Data Index: 8001088 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.6040. Min Act: -0.1700
Data Index: 6942242 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.5415. Min Act: -0.1700
Data Index: 6595754 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.5415. Min Act: -0.1700
Data Index: 3541236 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.4790. Min Act: -0.1700
Data Index: 3199642 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.4790. Min Act: -0.1700
Data Index: 8463645 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.4165. Min Act: -0.1700
Data Index: 5243808 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.2915. Min Act: -0.1700
Data Index: 6846292 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.2915. Min Act: -0.1700
Data Index: 3372944 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.2602. Min Act: -0.1700
Data Index: 117246 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.2290. Min Act: -0.1700
Data Index: 952763 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.1665. Min Act: -0.1700
Data Index: 7620831 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.1665. Min Act: -0.1700
Data Index: 526530 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.1977. Min Act: -0.1700
Data Index: 3095368 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.1352. Min Act: -0.1700
Data Index: 3899511 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.1352. Min Act: -0.1700
Data Index: 510413 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9165. Min Range: -8.9165
Max Act: 8.1040. Min Act: -0.1700
Data Index: 4328858 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19