Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 108 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.6356. Min Act: -0.1700
Data Index: 3426215 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.4481. Min Act: -0.1700
Data Index: 5806160 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.4481. Min Act: -0.1700
Data Index: 7208062 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.4481. Min Act: -0.1700
Data Index: 5768692 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.3856. Min Act: -0.1700
Data Index: 7324899 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.2918. Min Act: -0.1700
Data Index: 5621297 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.1981. Min Act: -0.1700
Data Index: 2926956 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.1356. Min Act: -0.1700
Data Index: 8585712 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.1356. Min Act: -0.1700
Data Index: 1361110 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.1043. Min Act: -0.1700
Data Index: 17391 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.1043. Min Act: -0.1700
Data Index: 171509 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.1043. Min Act: -0.1700
Data Index: 2347551 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.0731. Min Act: -0.1700
Data Index: 7823813 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.0731. Min Act: -0.1700
Data Index: 4130361 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.0106. Min Act: -0.1700
Data Index: 5806158 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6356. Min Range: -8.6356
Max Act: 8.0106. Min Act: -0.1700
Data Index: 5768694 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6356. Min Range: -8.6356
Max Act: 7.9793. Min Act: -0.1700
Data Index: 2828653 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6356. Min Range: -8.6356
Max Act: 7.9168. Min Act: -0.1700
Data Index: 6148151 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6356. Min Range: -8.6356
Max Act: 7.9168. Min Act: -0.1700
Data Index: 3248696 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6356. Min Range: -8.6356
Max Act: 7.9793. Min Act: -0.1700
Data Index: 112307 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19