Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.3826. Min Act: -0.1700
Data Index: 5547504 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.3513. Min Act: -0.1700
Data Index: 4913633 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.3201. Min Act: -0.1700
Data Index: 2169078 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.2576. Min Act: -0.1700
Data Index: 6847227 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.1951. Min Act: -0.1700
Data Index: 1808245 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.1326. Min Act: -0.1700
Data Index: 7510642 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.1013. Min Act: -0.1700
Data Index: 6422737 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.0701. Min Act: -0.1700
Data Index: 2640053 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.0701. Min Act: -0.1700
Data Index: 5919156 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.0388. Min Act: -0.1700
Data Index: 3612097 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.0388. Min Act: -0.1700
Data Index: 6834447 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.0076. Min Act: -0.1700
Data Index: 8653981 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.0076. Min Act: -0.1700
Data Index: 5131699 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.9138. Min Act: -0.1700
Data Index: 7306308 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.9138. Min Act: -0.1700
Data Index: 533175 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.9138. Min Act: -0.1700
Data Index: 2436526 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.9138. Min Act: -0.1700
Data Index: 5919160 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.9138. Min Act: -0.1700
Data Index: 1914092 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.9451. Min Act: -0.1700
Data Index: 3802533 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.8826. Min Act: -0.1700
Data Index: 3971909 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19