Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5106 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.8585. Min Act: -0.1700
Data Index: 4669078 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.5460. Min Act: -0.1700
Data Index: 6341407 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.4835. Min Act: -0.1700
Data Index: 5423104 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.4835. Min Act: -0.1700
Data Index: 2441024 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.4835. Min Act: -0.1700
Data Index: 1824268 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.4835. Min Act: -0.1700
Data Index: 6171936 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.4835. Min Act: -0.1700
Data Index: 2014455 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.4210. Min Act: -0.1700
Data Index: 579479 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.4210. Min Act: -0.1700
Data Index: 1275906 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.3585. Min Act: -0.1700
Data Index: 8535901 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.3585. Min Act: -0.1700
Data Index: 6242318 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.2960. Min Act: -0.1700
Data Index: 115904 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.2335. Min Act: -0.1700
Data Index: 1741116 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.2335. Min Act: -0.1700
Data Index: 4786512 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.1710. Min Act: -0.1700
Data Index: 1150884 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.2335. Min Act: -0.1700
Data Index: 2463785 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.1085. Min Act: -0.1700
Data Index: 5819006 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.1085. Min Act: -0.1700
Data Index: 2034189 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.0460. Min Act: -0.1700
Data Index: 498738 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8585. Min Range: -8.8585
Max Act: 8.0460. Min Act: -0.1700
Data Index: 8197854 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19