Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4473 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2905. Min Range: -8.2905
Max Act: 8.2905. Min Act: -0.1700
Data Index: 96305 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2905. Min Range: -8.2905
Max Act: 8.1030. Min Act: -0.1700
Data Index: 324005 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2905. Min Range: -8.2905
Max Act: 8.1030. Min Act: -0.1700
Data Index: 8261496 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2905. Min Range: -8.2905
Max Act: 8.1030. Min Act: -0.1700
Data Index: 3189705 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.9155. Min Act: -0.1700
Data Index: 7341985 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.8530. Min Act: -0.1700
Data Index: 2520141 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.8530. Min Act: -0.1700
Data Index: 7352650 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 4678736 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 181301 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7905. Min Act: -0.1700
Data Index: 4299575 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 7321979 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 7371184 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 7745882 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 179603 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 659177 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 1124878 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.6655. Min Act: -0.1700
Data Index: 7024780 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 2340698 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.6655. Min Act: -0.1700
Data Index: 6700339 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2905. Min Range: -8.2905
Max Act: 7.6655. Min Act: -0.1700
Data Index: 1498833 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19