Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.5368. Min Act: -0.1700
Data Index: 1237742 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.5055. Min Act: -0.1700
Data Index: 3850342 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.5055. Min Act: -0.1700
Data Index: 2943226 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.5055. Min Act: -0.1700
Data Index: 7777381 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.4430. Min Act: -0.1700
Data Index: 5415886 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.4430. Min Act: -0.1700
Data Index: 7738985 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.4118. Min Act: -0.1700
Data Index: 4153304 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.4430. Min Act: -0.1700
Data Index: 7201553 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.4118. Min Act: -0.1700
Data Index: 8696822 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.4118. Min Act: -0.1700
Data Index: 5254821 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3805. Min Act: -0.1700
Data Index: 7356592 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3805. Min Act: -0.1700
Data Index: 4569882 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3805. Min Act: -0.1700
Data Index: 6797696 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3805. Min Act: -0.1700
Data Index: 314584 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3805. Min Act: -0.1700
Data Index: 1421164 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3493. Min Act: -0.1700
Data Index: 2260300 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3493. Min Act: -0.1700
Data Index: 5809697 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3180. Min Act: -0.1700
Data Index: 5306162 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3180. Min Act: -0.1700
Data Index: 658737 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5368. Min Range: -6.5368
Max Act: 6.3180. Min Act: -0.1700
Data Index: 5516434 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19