Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3405. Min Act: -0.1700
Data Index: 2101441 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 3688418 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 3578022 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3093. Min Act: -0.1700
Data Index: 7021644 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2468. Min Act: -0.1700
Data Index: 4882457 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 3057804 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2468. Min Act: -0.1700
Data Index: 3703299 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2155. Min Act: -0.1700
Data Index: 3042853 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2155. Min Act: -0.1700
Data Index: 1916706 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2155. Min Act: -0.1700
Data Index: 2642880 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2155. Min Act: -0.1700
Data Index: 794668 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2155. Min Act: -0.1700
Data Index: 6325986 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1843. Min Act: -0.1700
Data Index: 7965550 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1843. Min Act: -0.1700
Data Index: 6159155 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1843. Min Act: -0.1700
Data Index: 1697497 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1843. Min Act: -0.1700
Data Index: 1176134 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1843. Min Act: -0.1700
Data Index: 4724888 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1843. Min Act: -0.1700
Data Index: 3917073 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1843. Min Act: -0.1700
Data Index: 3742486 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1700
Data Index: 814499 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19