Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1189 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.7322. Min Act: -0.1700
Data Index: 170098 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.5447. Min Act: -0.1700
Data Index: 3824630 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.4822. Min Act: -0.1700
Data Index: 8583368 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.2947. Min Act: -0.1700
Data Index: 7588140 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.2322. Min Act: -0.1700
Data Index: 5386956 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.2322. Min Act: -0.1700
Data Index: 630291 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.1697. Min Act: -0.1700
Data Index: 8416473 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.1697. Min Act: -0.1700
Data Index: 8691484 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.1697. Min Act: -0.1700
Data Index: 8624062 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.1072. Min Act: -0.1700
Data Index: 8371755 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.1072. Min Act: -0.1700
Data Index: 7237616 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7322. Min Range: -10.7322
Max Act: 9.9822. Min Act: -0.1700
Data Index: 1531602 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.1072. Min Act: -0.1700
Data Index: 7287865 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.0447. Min Act: -0.1700
Data Index: 3649764 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7322. Min Range: -10.7322
Max Act: 10.0447. Min Act: -0.1700
Data Index: 5650688 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7322. Min Range: -10.7322
Max Act: 9.9822. Min Act: -0.1700
Data Index: 6893366 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7322. Min Range: -10.7322
Max Act: 9.9822. Min Act: -0.1698
Data Index: 8568406 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7322. Min Range: -10.7322
Max Act: 9.9822. Min Act: -0.1700
Data Index: 5298573 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7322. Min Range: -10.7322
Max Act: 9.9197. Min Act: -0.1700
Data Index: 4577164 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7322. Min Range: -10.7322
Max Act: 9.8572. Min Act: -0.1700
Data Index: 6308305 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19