Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 712 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.8274. Min Act: -0.1700
Data Index: 3000674 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.7649. Min Act: -0.1700
Data Index: 2031237 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.7649. Min Act: -0.1700
Data Index: 7375935 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.5149. Min Act: -0.1700
Data Index: 8074140 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.5149. Min Act: -0.1700
Data Index: 3860007 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.5149. Min Act: -0.1700
Data Index: 2282390 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.5149. Min Act: -0.1700
Data Index: 671140 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.4524. Min Act: -0.1700
Data Index: 6029415 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.4524. Min Act: -0.1700
Data Index: 7862371 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.3899. Min Act: -0.1700
Data Index: 8198038 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.4524. Min Act: -0.1700
Data Index: 5657789 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.4524. Min Act: -0.1700
Data Index: 5392081 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.3899. Min Act: -0.1700
Data Index: 5308777 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.3899. Min Act: -0.1700
Data Index: 2413321 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.4524. Min Act: -0.1700
Data Index: 6930661 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.3274. Min Act: -0.1700
Data Index: 1248296 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.3274. Min Act: -0.1700
Data Index: 4782660 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.3274. Min Act: -0.1700
Data Index: 8468417 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.3274. Min Act: -0.1700
Data Index: 3124620 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8274. Min Range: -10.8274
Max Act: 10.3274. Min Act: -0.1700
Data Index: 2371199 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19