Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2361 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3037. Min Range: -7.3037
Max Act: 7.3037. Min Act: -0.1700
Data Index: 7050369 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3037. Min Range: -7.3037
Max Act: 7.1787. Min Act: -0.1700
Data Index: 3884421 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3037. Min Range: -7.3037
Max Act: 7.1162. Min Act: -0.1700
Data Index: 6807537 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3037. Min Range: -7.3037
Max Act: 7.0537. Min Act: -0.1700
Data Index: 6994705 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3037. Min Range: -7.3037
Max Act: 7.0225. Min Act: -0.1700
Data Index: 3567503 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.8350. Min Act: -0.1700
Data Index: 8728756 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.8662. Min Act: -0.1700
Data Index: 6586182 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.8037. Min Act: -0.1700
Data Index: 7912883 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.7725. Min Act: -0.1700
Data Index: 5128122 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.7725. Min Act: -0.1700
Data Index: 1994641 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.7725. Min Act: -0.1700
Data Index: 4961541 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.7412. Min Act: -0.1700
Data Index: 1251061 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.7412. Min Act: -0.1700
Data Index: 6907872 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.7100. Min Act: -0.1700
Data Index: 8666342 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.6787. Min Act: -0.1700
Data Index: 2259204 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.6787. Min Act: -0.1700
Data Index: 5870995 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.6475. Min Act: -0.1700
Data Index: 7929234 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.6475. Min Act: -0.1700
Data Index: 1789551 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.6162. Min Act: -0.1700
Data Index: 6476858 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3037. Min Range: -7.3037
Max Act: 6.6162. Min Act: -0.1700
Data Index: 4522710 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19