Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.8385. Min Act: -0.1700
Data Index: 3029728 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.8072. Min Act: -0.1700
Data Index: 3555168 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.7135. Min Act: -0.1700
Data Index: 3087409 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.6197. Min Act: -0.1700
Data Index: 8756627 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.5260. Min Act: -0.1700
Data Index: 3379541 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.4947. Min Act: -0.1700
Data Index: 531041 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.4635. Min Act: -0.1700
Data Index: 978507 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.4635. Min Act: -0.1700
Data Index: 6571483 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.4322. Min Act: -0.1700
Data Index: 3785711 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.4322. Min Act: -0.1700
Data Index: 941323 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.4322. Min Act: -0.1700
Data Index: 1061922 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.4322. Min Act: -0.1700
Data Index: 2676589 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.4322. Min Act: -0.1700
Data Index: 3440326 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3697. Min Act: -0.1700
Data Index: 4843752 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3697. Min Act: -0.1700
Data Index: 3570577 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3697. Min Act: -0.1700
Data Index: 4364783 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3385. Min Act: -0.1700
Data Index: 8467768 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3385. Min Act: -0.1700
Data Index: 1324186 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3072. Min Act: -0.1700
Data Index: 5612745 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3072. Min Act: -0.1700
Data Index: 1824255 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19