Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 979 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.5707. Min Act: -0.1700
Data Index: 689953 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.5707. Min Act: -0.1700
Data Index: 7050688 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.5384. Min Act: -0.1700
Data Index: 6754239 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.5223. Min Act: -0.1700
Data Index: 2613774 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.5061. Min Act: -0.1700
Data Index: 547509 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.5223. Min Act: -0.1700
Data Index: 5867574 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4737. Min Act: -0.1700
Data Index: 8755302 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4899. Min Act: -0.1700
Data Index: 7139469 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.5061. Min Act: -0.1700
Data Index: 8700605 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4737. Min Act: -0.1700
Data Index: 7751098 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4737. Min Act: -0.1700
Data Index: 403015 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4737. Min Act: -0.1700
Data Index: 1878104 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4737. Min Act: -0.1700
Data Index: 3187351 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4899. Min Act: -0.1700
Data Index: 4663660 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4574. Min Act: -0.1700
Data Index: 7982574 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4574. Min Act: -0.1700
Data Index: 1787234 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4574. Min Act: -0.1700
Data Index: 368434 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4412. Min Act: -0.1700
Data Index: 3155580 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4412. Min Act: -0.1700
Data Index: 5799300 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5707. Min Range: -2.5707
Max Act: 2.4412. Min Act: -0.1700
Data Index: 2221432 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19