Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4705 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.5108. Min Act: -0.1700
Data Index: 3105575 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.1983. Min Act: -0.1700
Data Index: 7946940 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.1983. Min Act: -0.1700
Data Index: 1990054 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.1358. Min Act: -0.1700
Data Index: 7459352 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.1358. Min Act: -0.1700
Data Index: 4147245 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.1358. Min Act: -0.1700
Data Index: 2339055 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.0733. Min Act: -0.1700
Data Index: 5230576 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.0733. Min Act: -0.1700
Data Index: 4249192 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.0733. Min Act: -0.1700
Data Index: 5293544 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.0108. Min Act: -0.1700
Data Index: 8730433 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.0108. Min Act: -0.1700
Data Index: 3730490 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.0108. Min Act: -0.1700
Data Index: 8712777 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5108. Min Range: -10.5108
Max Act: 9.8858. Min Act: -0.1700
Data Index: 8092983 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5108. Min Range: -10.5108
Max Act: 10.0108. Min Act: -0.1700
Data Index: 8561877 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5108. Min Range: -10.5108
Max Act: 9.8858. Min Act: -0.1700
Data Index: 1271106 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5108. Min Range: -10.5108
Max Act: 9.8858. Min Act: -0.1700
Data Index: 4346080 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5108. Min Range: -10.5108
Max Act: 9.8858. Min Act: -0.1700
Data Index: 3246087 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5108. Min Range: -10.5108
Max Act: 9.8858. Min Act: -0.1700
Data Index: 4538568 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5108. Min Range: -10.5108
Max Act: 9.8858. Min Act: -0.1700
Data Index: 618251 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5108. Min Range: -10.5108
Max Act: 9.8858. Min Act: -0.1700
Data Index: 138819 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19