Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.2539. Min Range: -14.2539
Max Act: 14.2539. Min Act: -0.1700
Data Index: 8625859 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.2539. Min Range: -14.2539
Max Act: 14.1914. Min Act: -0.1700
Data Index: 722779 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.2539. Min Range: -14.2539
Max Act: 14.0039. Min Act: -0.1700
Data Index: 1322447 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.9414. Min Act: -0.1700
Data Index: 3660822 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.8164. Min Act: -0.1700
Data Index: 5209472 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.5664. Min Act: -0.1700
Data Index: 7080730 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.5039. Min Act: -0.1700
Data Index: 6002284 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.4414. Min Act: -0.1700
Data Index: 1981110 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.4414. Min Act: -0.1700
Data Index: 542111 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.3789. Min Act: -0.1700
Data Index: 1590131 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.3789. Min Act: -0.1700
Data Index: 8151461 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.4414. Min Act: -0.1700
Data Index: 5083815 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.3789. Min Act: -0.1700
Data Index: 7351318 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.3789. Min Act: -0.1700
Data Index: 850932 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.2539. Min Act: -0.1700
Data Index: 8377330 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.1914. Min Act: -0.1700
Data Index: 6938346 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.1914. Min Act: -0.1700
Data Index: 4386845 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.1914. Min Act: -0.1700
Data Index: 4007834 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.1914. Min Act: -0.1700
Data Index: 34241 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.2539. Min Range: -14.2539
Max Act: 13.1914. Min Act: -0.1700
Data Index: 1348794 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19