Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4157 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.8107. Min Act: -0.1700
Data Index: 500674 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.4357. Min Act: -0.1700
Data Index: 4762926 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.3732. Min Act: -0.1700
Data Index: 8349405 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.3732. Min Act: -0.1700
Data Index: 6421071 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.3732. Min Act: -0.1700
Data Index: 767737 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.3732. Min Act: -0.1700
Data Index: 6793455 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.3107. Min Act: -0.1700
Data Index: 7731746 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.3107. Min Act: -0.1700
Data Index: 82208 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.3107. Min Act: -0.1700
Data Index: 8313663 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.3107. Min Act: -0.1700
Data Index: 3898142 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.2482. Min Act: -0.1700
Data Index: 6024144 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.3107. Min Act: -0.1700
Data Index: 500666 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.2482. Min Act: -0.1700
Data Index: 6789068 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.2482. Min Act: -0.1700
Data Index: 2812643 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.2482. Min Act: -0.1700
Data Index: 5944559 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.2482. Min Act: -0.1700
Data Index: 3753526 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.2482. Min Act: -0.1700
Data Index: 7124727 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.1857. Min Act: -0.1700
Data Index: 8732315 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.2482. Min Act: -0.1700
Data Index: 1435164 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8107. Min Range: -9.8107
Max Act: 9.1857. Min Act: -0.1700
Data Index: 2489846 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19