Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.9726. Min Act: -0.1700
Data Index: 1462520 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0039. Min Range: -7.0039
Max Act: 7.0039. Min Act: -0.1700
Data Index: 2458078 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.9414. Min Act: -0.1700
Data Index: 1056834 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.8164. Min Act: -0.1700
Data Index: 1874520 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.8164. Min Act: -0.1700
Data Index: 6803874 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.7851. Min Act: -0.1700
Data Index: 495040 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.7851. Min Act: -0.1700
Data Index: 8200372 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.7226. Min Act: -0.1700
Data Index: 7359688 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.6914. Min Act: -0.1700
Data Index: 2186821 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.6914. Min Act: -0.1700
Data Index: 4873537 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.6601. Min Act: -0.1700
Data Index: 7901266 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.6289. Min Act: -0.1700
Data Index: 2503816 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.6289. Min Act: -0.1700
Data Index: 116307 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.5976. Min Act: -0.1700
Data Index: 6488427 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.5976. Min Act: -0.1700
Data Index: 5503264 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.5976. Min Act: -0.1700
Data Index: 3897282 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.6289. Min Act: -0.1700
Data Index: 5629210 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.5664. Min Act: -0.1700
Data Index: 4792014 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.5664. Min Act: -0.1700
Data Index: 6618126 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0039. Min Range: -7.0039
Max Act: 6.5351. Min Act: -0.1700
Data Index: 2645769 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19