Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 328 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3164. Min Range: -9.3164
Max Act: 9.3164. Min Act: -0.1700
Data Index: 983713 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3164. Min Range: -9.3164
Max Act: 9.0664. Min Act: -0.1700
Data Index: 2397141 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3164. Min Range: -9.3164
Max Act: 9.0664. Min Act: -0.1700
Data Index: 6109876 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3164. Min Range: -9.3164
Max Act: 9.0039. Min Act: -0.1700
Data Index: 5514798 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3164. Min Range: -9.3164
Max Act: 9.0039. Min Act: -0.1700
Data Index: 7894242 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3164. Min Range: -9.3164
Max Act: 9.0039. Min Act: -0.1700
Data Index: 4197270 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3164. Min Range: -9.3164
Max Act: 9.0039. Min Act: -0.1700
Data Index: 1558070 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.9414. Min Act: -0.1700
Data Index: 3590231 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.9414. Min Act: -0.1700
Data Index: 2542214 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.9414. Min Act: -0.1700
Data Index: 4882724 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.9414. Min Act: -0.1700
Data Index: 2028095 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.8789. Min Act: -0.1700
Data Index: 1406159 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.8789. Min Act: -0.1700
Data Index: 2401739 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.8789. Min Act: -0.1700
Data Index: 8349386 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.8789. Min Act: -0.1700
Data Index: 6383727 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.8164. Min Act: -0.1700
Data Index: 4333765 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.8164. Min Act: -0.1700
Data Index: 5870412 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.8164. Min Act: -0.1700
Data Index: 1561180 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.8164. Min Act: -0.1700
Data Index: 3655144 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3164. Min Range: -9.3164
Max Act: 8.8164. Min Act: -0.1700
Data Index: 3572747 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19