Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1472 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2036. Min Range: -8.2036
Max Act: 8.2036. Min Act: -0.1700
Data Index: 4711870 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.8911. Min Act: -0.1700
Data Index: 1085559 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.7974. Min Act: -0.1700
Data Index: 6521478 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.7349. Min Act: -0.1700
Data Index: 7943597 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.5474. Min Act: -0.1700
Data Index: 6716548 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.5474. Min Act: -0.1700
Data Index: 7045549 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.5474. Min Act: -0.1700
Data Index: 5660258 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.4224. Min Act: -0.1700
Data Index: 5777989 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.4536. Min Act: -0.1700
Data Index: 6081131 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.3286. Min Act: -0.1700
Data Index: 5397959 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.3599. Min Act: -0.1700
Data Index: 1575979 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.2974. Min Act: -0.1700
Data Index: 5511852 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.2661. Min Act: -0.1700
Data Index: 6610861 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.2661. Min Act: -0.1700
Data Index: 5573132 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.2661. Min Act: -0.1700
Data Index: 2820867 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.2036. Min Act: -0.1700
Data Index: 254394 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.1724. Min Act: -0.1700
Data Index: 1679868 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.1411. Min Act: -0.1700
Data Index: 2571565 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.1411. Min Act: -0.1700
Data Index: 3529915 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2036. Min Range: -8.2036
Max Act: 7.1411. Min Act: -0.1700
Data Index: 2719147 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19