Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2486 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.3766. Min Range: -16.3766
Max Act: 16.3766. Min Act: -0.1700
Data Index: 5647699 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.3766. Min Range: -16.3766
Max Act: 16.3766. Min Act: -0.1700
Data Index: 5352095 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.3766. Min Range: -16.3766
Max Act: 16.2516. Min Act: -0.1700
Data Index: 1898234 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.8766. Min Act: -0.1700
Data Index: 3897013 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.8766. Min Act: -0.1700
Data Index: 8526004 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.8766. Min Act: -0.1700
Data Index: 8519698 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.8766. Min Act: -0.1700
Data Index: 3737708 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.8766. Min Act: -0.1700
Data Index: 5474106 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.8766. Min Act: -0.1700
Data Index: 6042414 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.7516. Min Act: -0.1700
Data Index: 2721784 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.6891. Min Act: -0.1700
Data Index: 951834 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.6266. Min Act: -0.1700
Data Index: 8014806 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.6266. Min Act: -0.1700
Data Index: 1720945 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.6266. Min Act: -0.1700
Data Index: 4989999 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.6266. Min Act: -0.1700
Data Index: 5689850 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.5641. Min Act: -0.1700
Data Index: 2873178 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.5641. Min Act: -0.1700
Data Index: 914547 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.5641. Min Act: -0.1700
Data Index: 7563675 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.5641. Min Act: -0.1700
Data Index: 4279872 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.3766. Min Range: -16.3766
Max Act: 15.5016. Min Act: -0.1700
Data Index: 4199341 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19