Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.7289. Min Act: -0.1700
Data Index: 313997 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.6664. Min Act: -0.1700
Data Index: 1751289 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.6039. Min Act: -0.1700
Data Index: 8230753 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.6039. Min Act: -0.1700
Data Index: 7683453 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.6039. Min Act: -0.1700
Data Index: 7605786 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.6039. Min Act: -0.1700
Data Index: 1015154 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.5414. Min Act: -0.1700
Data Index: 8097932 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.4789. Min Act: -0.1700
Data Index: 4190435 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.4789. Min Act: -0.1700
Data Index: 580884 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.4789. Min Act: -0.1700
Data Index: 6267254 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.4164. Min Act: -0.1700
Data Index: 8231765 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.4164. Min Act: -0.1700
Data Index: 6883216 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.4164. Min Act: -0.1700
Data Index: 7063253 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.4164. Min Act: -0.1700
Data Index: 2295789 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.4164. Min Act: -0.1700
Data Index: 4348919 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.4164. Min Act: -0.1700
Data Index: 2155535 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.3539. Min Act: -0.1700
Data Index: 5844787 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.3539. Min Act: -0.1700
Data Index: 3638672 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.2914. Min Act: -0.1700
Data Index: 767889 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7289. Min Range: -8.7289
Max Act: 8.2914. Min Act: -0.1700
Data Index: 3464366 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19