Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6046 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1251. Min Range: -8.1251
Max Act: 8.1251. Min Act: -0.1700
Data Index: 6296893 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.8751. Min Act: -0.1700
Data Index: 6467780 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.8438. Min Act: -0.1700
Data Index: 8195184 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.8438. Min Act: -0.1700
Data Index: 726938 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.8126. Min Act: -0.1700
Data Index: 6504422 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.8126. Min Act: -0.1700
Data Index: 5323969 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.7813. Min Act: -0.1700
Data Index: 5987698 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.7813. Min Act: -0.1700
Data Index: 789584 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.7501. Min Act: -0.1700
Data Index: 568499 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.7188. Min Act: -0.1700
Data Index: 2692917 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.7813. Min Act: -0.1700
Data Index: 853384 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.7501. Min Act: -0.1700
Data Index: 3708131 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.7188. Min Act: -0.1700
Data Index: 132411 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.6563. Min Act: -0.1700
Data Index: 2981930 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.6876. Min Act: -0.1700
Data Index: 3452953 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.6876. Min Act: -0.1700
Data Index: 1966497 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.6563. Min Act: -0.1700
Data Index: 4010466 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.6251. Min Act: -0.1700
Data Index: 367202 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.6251. Min Act: -0.1700
Data Index: 2381118 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1251. Min Range: -8.1251
Max Act: 7.6251. Min Act: -0.1700
Data Index: 2040105 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19