Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5062 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8886. Min Act: -0.1700
Data Index: 1878903 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8261. Min Act: -0.1700
Data Index: 2085906 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7635. Min Act: -0.1700
Data Index: 3780913 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7479. Min Act: -0.1700
Data Index: 2919426 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7166. Min Act: -0.1700
Data Index: 1930451 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6853. Min Act: -0.1700
Data Index: 1804900 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7009. Min Act: -0.1700
Data Index: 5641483 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6697. Min Act: -0.1700
Data Index: 382252 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6853. Min Act: -0.1700
Data Index: 387348 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6853. Min Act: -0.1700
Data Index: 1392288 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6853. Min Act: -0.1700
Data Index: 4674790 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6853. Min Act: -0.1700
Data Index: 3944744 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6697. Min Act: -0.1700
Data Index: 4947341 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6540. Min Act: -0.1700
Data Index: 7913842 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6227. Min Act: -0.1700
Data Index: 7417517 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6227. Min Act: -0.1700
Data Index: 3183050 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6227. Min Act: -0.1700
Data Index: 7066301 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.5758. Min Act: -0.1700
Data Index: 2536630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6071. Min Act: -0.1700
Data Index: 2749951 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6071. Min Act: -0.1700
Data Index: 4193579 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19