Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.5414. Min Act: -0.1700
Data Index: 5356879 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.4476. Min Act: -0.1700
Data Index: 205859 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.4164. Min Act: -0.1700
Data Index: 800747 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.3851. Min Act: -0.1700
Data Index: 2754563 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.3226. Min Act: -0.1700
Data Index: 4099905 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.2601. Min Act: -0.1700
Data Index: 2730125 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.2601. Min Act: -0.1700
Data Index: 2535736 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.2289. Min Act: -0.1700
Data Index: 8558343 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.2289. Min Act: -0.1700
Data Index: 2344154 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.1976. Min Act: -0.1700
Data Index: 8150137 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.1976. Min Act: -0.1700
Data Index: 4351796 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.1976. Min Act: -0.1700
Data Index: 1096366 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.1351. Min Act: -0.1700
Data Index: 4108873 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.1351. Min Act: -0.1700
Data Index: 162867 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.1351. Min Act: -0.1700
Data Index: 1060630 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.1039. Min Act: -0.1700
Data Index: 6287671 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.0726. Min Act: -0.1700
Data Index: 8759445 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.0726. Min Act: -0.1700
Data Index: 2193569 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.0726. Min Act: -0.1700
Data Index: 8220449 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5414. Min Range: -7.5414
Max Act: 7.0414. Min Act: -0.1700
Data Index: 4138911 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19