Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 693 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0066. Min Range: -6.0066
Max Act: 6.0066. Min Act: -0.1700
Data Index: 3387242 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.9129. Min Act: -0.1700
Data Index: 6758038 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.8816. Min Act: -0.1700
Data Index: 2294606 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.8504. Min Act: -0.1700
Data Index: 7195231 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.8191. Min Act: -0.1700
Data Index: 6048310 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.7879. Min Act: -0.1700
Data Index: 8160343 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.7879. Min Act: -0.1700
Data Index: 1492502 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.7254. Min Act: -0.1700
Data Index: 3134504 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.6629. Min Act: -0.1700
Data Index: 6120296 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.6941. Min Act: -0.1700
Data Index: 8806660 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.6316. Min Act: -0.1700
Data Index: 3661752 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.6316. Min Act: -0.1700
Data Index: 677586 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.5691. Min Act: -0.1700
Data Index: 4984197 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.6004. Min Act: -0.1700
Data Index: 194030 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.6004. Min Act: -0.1700
Data Index: 4984502 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.6004. Min Act: -0.1700
Data Index: 6814047 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.6004. Min Act: -0.1700
Data Index: 6795815 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.5691. Min Act: -0.1700
Data Index: 2045680 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.5691. Min Act: -0.1700
Data Index: 1739512 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0066. Min Range: -6.0066
Max Act: 5.5379. Min Act: -0.1700
Data Index: 7955966 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19