Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.9891. Min Act: -0.1700
Data Index: 3375000 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.9266. Min Act: -0.1700
Data Index: 4516575 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.8954. Min Act: -0.1700
Data Index: 2211417 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.8016. Min Act: -0.1700
Data Index: 7212815 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.7391. Min Act: -0.1700
Data Index: 6942127 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.7079. Min Act: -0.1700
Data Index: 7774810 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.7079. Min Act: -0.1700
Data Index: 5866993 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6766. Min Act: -0.1700
Data Index: 7173144 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6766. Min Act: -0.1700
Data Index: 23186 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6454. Min Act: -0.1700
Data Index: 632328 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6454. Min Act: -0.1700
Data Index: 6942123 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6454. Min Act: -0.1700
Data Index: 6579129 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6141. Min Act: -0.1700
Data Index: 3059379 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6141. Min Act: -0.1700
Data Index: 5174978 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6141. Min Act: -0.1700
Data Index: 2240311 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6141. Min Act: -0.1700
Data Index: 1074624 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.6141. Min Act: -0.1700
Data Index: 6060350 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.5829. Min Act: -0.1700
Data Index: 6631602 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.5516. Min Act: -0.1700
Data Index: 6695321 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9891. Min Range: -6.9891
Max Act: 6.5829. Min Act: -0.1700
Data Index: 5211896 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19