Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2911. Min Range: -6.2911
Max Act: 6.2911. Min Act: -0.1700
Data Index: 5581847 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2911. Min Range: -6.2911
Max Act: 6.1973. Min Act: -0.1700
Data Index: 3250243 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2911. Min Range: -6.2911
Max Act: 6.1348. Min Act: -0.1700
Data Index: 742322 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.9786. Min Act: -0.1700
Data Index: 2593444 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.8848. Min Act: -0.1700
Data Index: 3034216 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.8848. Min Act: -0.1700
Data Index: 3438270 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.8848. Min Act: -0.1700
Data Index: 239930 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.8848. Min Act: -0.1700
Data Index: 2837028 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.8536. Min Act: -0.1700
Data Index: 5167586 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.8536. Min Act: -0.1700
Data Index: 7418287 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.8223. Min Act: -0.1700
Data Index: 4176379 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.7911. Min Act: -0.1700
Data Index: 7116838 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.7911. Min Act: -0.1700
Data Index: 225398 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.7598. Min Act: -0.1700
Data Index: 121574 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.7911. Min Act: -0.1700
Data Index: 3483279 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.7286. Min Act: -0.1700
Data Index: 4928539 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.7598. Min Act: -0.1700
Data Index: 8034546 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.7286. Min Act: -0.1700
Data Index: 1090192 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.7286. Min Act: -0.1700
Data Index: 228406 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2911. Min Range: -6.2911
Max Act: 5.7286. Min Act: -0.1700
Data Index: 3380488 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19