Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6034 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.9206. Min Act: -0.1700
Data Index: 8328875 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.8111. Min Act: -0.1700
Data Index: 5463240 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.7955. Min Act: -0.1700
Data Index: 8125705 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.7486. Min Act: -0.1700
Data Index: 8353744 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.7017. Min Act: -0.1700
Data Index: 2517703 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.7173. Min Act: -0.1700
Data Index: 4624622 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6860. Min Act: -0.1700
Data Index: 1308720 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6860. Min Act: -0.1700
Data Index: 305867 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6704. Min Act: -0.1700
Data Index: 8797924 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6704. Min Act: -0.1700
Data Index: 131080 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6391. Min Act: -0.1700
Data Index: 2939971 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6391. Min Act: -0.1700
Data Index: 8471121 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6234. Min Act: -0.1700
Data Index: 557413 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6234. Min Act: -0.1700
Data Index: 2055455 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6234. Min Act: -0.1700
Data Index: 7760546 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6234. Min Act: -0.1700
Data Index: 3407711 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.6234. Min Act: -0.1700
Data Index: 2446371 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.5765. Min Act: -0.1700
Data Index: 759365 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.5452. Min Act: -0.1700
Data Index: 6081268 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9206. Min Range: -3.9206
Max Act: 3.5608. Min Act: -0.1700
Data Index: 8794233 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19