Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2281. Min Range: -6.2281
Max Act: 6.2281. Min Act: -0.1700
Data Index: 326541 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2281. Min Range: -6.2281
Max Act: 6.0406. Min Act: -0.1700
Data Index: 2169556 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9781. Min Act: -0.1700
Data Index: 6575412 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9781. Min Act: -0.1700
Data Index: 4245021 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9469. Min Act: -0.1700
Data Index: 844771 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9469. Min Act: -0.1700
Data Index: 4245022 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 6548727 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 1688835 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 1357372 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 8247763 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 2813817 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 7609623 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 3580034 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 2412334 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 6175053 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.8844. Min Act: -0.1700
Data Index: 2529953 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.8844. Min Act: -0.1700
Data Index: 6648536 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.8844. Min Act: -0.1700
Data Index: 2257504 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.9156. Min Act: -0.1700
Data Index: 5654855 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2281. Min Range: -6.2281
Max Act: 5.8531. Min Act: -0.1700
Data Index: 4977909 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19