Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1097 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.8343. Min Act: -0.1700
Data Index: 3136146 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.7718. Min Act: -0.1700
Data Index: 6116629 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.7718. Min Act: -0.1700
Data Index: 3688062 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.7406. Min Act: -0.1700
Data Index: 8588700 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.6781. Min Act: -0.1700
Data Index: 1051369 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.6468. Min Act: -0.1700
Data Index: 8163058 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.6156. Min Act: -0.1700
Data Index: 3996319 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.6156. Min Act: -0.1700
Data Index: 7755872 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5843. Min Act: -0.1700
Data Index: 4023631 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5843. Min Act: -0.1700
Data Index: 997327 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5531. Min Act: -0.1700
Data Index: 5280558 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5843. Min Act: -0.1700
Data Index: 4118590 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5843. Min Act: -0.1700
Data Index: 416283 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5843. Min Act: -0.1700
Data Index: 2859116 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5531. Min Act: -0.1700
Data Index: 3290608 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5843. Min Act: -0.1700
Data Index: 2704032 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5218. Min Act: -0.1700
Data Index: 3363840 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5531. Min Act: -0.1700
Data Index: 6418883 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5531. Min Act: -0.1700
Data Index: 3752825 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8343. Min Range: -6.8343
Max Act: 6.5218. Min Act: -0.1700
Data Index: 6481230 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19