Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5566 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6725. Min Act: -0.1700
Data Index: 8513239 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6413. Min Act: -0.1700
Data Index: 5658280 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6413. Min Act: -0.1700
Data Index: 2571348 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6413. Min Act: -0.1700
Data Index: 4295418 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6100. Min Act: -0.1700
Data Index: 6461385 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6100. Min Act: -0.1700
Data Index: 3742929 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5788. Min Act: -0.1700
Data Index: 8197450 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6100. Min Act: -0.1700
Data Index: 8222439 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5788. Min Act: -0.1700
Data Index: 1820770 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5475. Min Act: -0.1700
Data Index: 1659861 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5475. Min Act: -0.1700
Data Index: 4805492 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5475. Min Act: -0.1700
Data Index: 3094386 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5475. Min Act: -0.1700
Data Index: 904231 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5475. Min Act: -0.1700
Data Index: 510593 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5475. Min Act: -0.1700
Data Index: 2607812 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5163. Min Act: -0.1700
Data Index: 3094387 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5163. Min Act: -0.1700
Data Index: 2515976 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4850. Min Act: -0.1700
Data Index: 4805491 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5163. Min Act: -0.1700
Data Index: 4864372 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5163. Min Act: -0.1700
Data Index: 5658282 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19