Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2425 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.8380. Min Act: -0.1700
Data Index: 7360065 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.8693. Min Act: -0.1700
Data Index: 7873903 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.8068. Min Act: -0.1700
Data Index: 6687633 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.7755. Min Act: -0.1700
Data Index: 2579304 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.7443. Min Act: -0.1700
Data Index: 8167159 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.7130. Min Act: -0.1700
Data Index: 4801504 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.6505. Min Act: -0.1700
Data Index: 1863913 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.6505. Min Act: -0.1700
Data Index: 7244842 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.6505. Min Act: -0.1700
Data Index: 3779631 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.6193. Min Act: -0.1700
Data Index: 6459114 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.6193. Min Act: -0.1700
Data Index: 6360279 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.6193. Min Act: -0.1700
Data Index: 6843227 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.5880. Min Act: -0.1700
Data Index: 4015699 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.6193. Min Act: -0.1700
Data Index: 7363531 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.5880. Min Act: -0.1700
Data Index: 4015700 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.5880. Min Act: -0.1700
Data Index: 7003544 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.5880. Min Act: -0.1700
Data Index: 5795531 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.5880. Min Act: -0.1700
Data Index: 5528337 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.5568. Min Act: -0.1700
Data Index: 6684920 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8693. Min Range: -6.8693
Max Act: 6.5880. Min Act: -0.1700
Data Index: 2515468 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19