Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1378 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.7632. Min Act: -0.1700
Data Index: 1727438 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.7007. Min Act: -0.1700
Data Index: 2435441 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.4194. Min Act: -0.1700
Data Index: 725350 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.2944. Min Act: -0.1700
Data Index: 1378424 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.2632. Min Act: -0.1700
Data Index: 2708883 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.2632. Min Act: -0.1700
Data Index: 5506162 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.2007. Min Act: -0.1700
Data Index: 3211106 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.1694. Min Act: -0.1700
Data Index: 211818 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.1382. Min Act: -0.1700
Data Index: 4715269 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.1694. Min Act: -0.1700
Data Index: 642401 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.1069. Min Act: -0.1700
Data Index: 456619 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.1382. Min Act: -0.1700
Data Index: 6316395 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.1069. Min Act: -0.1700
Data Index: 4162903 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.1069. Min Act: -0.1700
Data Index: 6319710 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.1069. Min Act: -0.1700
Data Index: 2690558 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.0444. Min Act: -0.1700
Data Index: 287303 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.0757. Min Act: -0.1700
Data Index: 963427 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.0444. Min Act: -0.1700
Data Index: 3532505 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.0132. Min Act: -0.1700
Data Index: 3323494 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7632. Min Range: -7.7632
Max Act: 7.0132. Min Act: -0.1700
Data Index: 4788158 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19