Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3821 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.8852. Min Act: -0.1700
Data Index: 8647870 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.7602. Min Act: -0.1700
Data Index: 6291285 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.7602. Min Act: -0.1700
Data Index: 6722192 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.6040. Min Act: -0.1700
Data Index: 6986084 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.6040. Min Act: -0.1700
Data Index: 7581091 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.6352. Min Act: -0.1700
Data Index: 2774698 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.5727. Min Act: -0.1700
Data Index: 133614 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.5727. Min Act: -0.1700
Data Index: 4630804 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.5415. Min Act: -0.1700
Data Index: 5054859 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.5102. Min Act: -0.1700
Data Index: 344691 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.5102. Min Act: -0.1700
Data Index: 770893 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.5102. Min Act: -0.1700
Data Index: 7536386 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.4790. Min Act: -0.1700
Data Index: 8566782 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.4477. Min Act: -0.1700
Data Index: 841532 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.4790. Min Act: -0.1700
Data Index: 904060 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.4165. Min Act: -0.1700
Data Index: 4924833 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.4477. Min Act: -0.1700
Data Index: 8732280 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.3540. Min Act: -0.1700
Data Index: 6034814 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.3852. Min Act: -0.1700
Data Index: 107272 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8852. Min Range: -6.8852
Max Act: 6.3540. Min Act: -0.1700
Data Index: 1145265 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19