Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.8740. Min Act: -0.1700
Data Index: 1935715 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.8740. Min Act: -0.1700
Data Index: 868566 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6863. Min Act: -0.1700
Data Index: 1156589 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6707. Min Act: -0.1700
Data Index: 3244343 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6707. Min Act: -0.1700
Data Index: 7671094 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6707. Min Act: -0.1700
Data Index: 3210812 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6707. Min Act: -0.1700
Data Index: 1060493 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6550. Min Act: -0.1700
Data Index: 5319638 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6394. Min Act: -0.1700
Data Index: 6147331 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6394. Min Act: -0.1700
Data Index: 5346350 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6081. Min Act: -0.1700
Data Index: 2498652 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6237. Min Act: -0.1700
Data Index: 4693113 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6237. Min Act: -0.1700
Data Index: 8807855 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.6394. Min Act: -0.1700
Data Index: 7985772 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.5924. Min Act: -0.1700
Data Index: 629812 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.5924. Min Act: -0.1700
Data Index: 7118626 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.5611. Min Act: -0.1700
Data Index: 1083055 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.5924. Min Act: -0.1700
Data Index: 8216752 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.5768. Min Act: -0.1700
Data Index: 3058739 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8740. Min Range: -3.8740
Max Act: 3.5611. Min Act: -0.1700
Data Index: 1032059 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19