Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5556 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4853. Min Range: -9.4853
Max Act: 9.4853. Min Act: -0.1700
Data Index: 5378621 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4853. Min Range: -9.4853
Max Act: 9.1728. Min Act: -0.1700
Data Index: 3805609 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4853. Min Range: -9.4853
Max Act: 9.1103. Min Act: -0.1700
Data Index: 2415344 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4853. Min Range: -9.4853
Max Act: 9.1103. Min Act: -0.1700
Data Index: 6491546 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4853. Min Range: -9.4853
Max Act: 9.0478. Min Act: -0.1700
Data Index: 5044723 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.9228. Min Act: -0.1700
Data Index: 6726751 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.9228. Min Act: -0.1700
Data Index: 3776707 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.9228. Min Act: -0.1700
Data Index: 8766482 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.8603. Min Act: -0.1700
Data Index: 6255296 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.8603. Min Act: -0.1700
Data Index: 8202803 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.8603. Min Act: -0.1700
Data Index: 6110466 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.7978. Min Act: -0.1700
Data Index: 5936284 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.7978. Min Act: -0.1700
Data Index: 2634533 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.7978. Min Act: -0.1700
Data Index: 4734326 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.7978. Min Act: -0.1700
Data Index: 7626202 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.7978. Min Act: -0.1700
Data Index: 1898232 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.7978. Min Act: -0.1700
Data Index: 8340686 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.7978. Min Act: -0.1700
Data Index: 5108774 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.7353. Min Act: -0.1700
Data Index: 8037161 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4853. Min Range: -9.4853
Max Act: 8.6728. Min Act: -0.1700
Data Index: 7502168 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19