Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1725. Min Range: -8.1725
Max Act: 8.1725. Min Act: -0.1700
Data Index: 3801579 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1725. Min Range: -8.1725
Max Act: 8.1725. Min Act: -0.1700
Data Index: 4007454 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1725. Min Range: -8.1725
Max Act: 8.1100. Min Act: -0.1700
Data Index: 1218454 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.9850. Min Act: -0.1700
Data Index: 7296766 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.9850. Min Act: -0.1700
Data Index: 1852767 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.9225. Min Act: -0.1700
Data Index: 6362836 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.9225. Min Act: -0.1700
Data Index: 1422280 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.9225. Min Act: -0.1700
Data Index: 2249944 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.9225. Min Act: -0.1700
Data Index: 295676 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.8600. Min Act: -0.1700
Data Index: 2724853 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.7350. Min Act: -0.1700
Data Index: 3269706 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.7975. Min Act: -0.1700
Data Index: 162078 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.7975. Min Act: -0.1700
Data Index: 897098 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.7975. Min Act: -0.1700
Data Index: 241245 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.7350. Min Act: -0.1700
Data Index: 6760441 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.7350. Min Act: -0.1700
Data Index: 3483156 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.7350. Min Act: -0.1700
Data Index: 2242751 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.6725. Min Act: -0.1700
Data Index: 7133764 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.6725. Min Act: -0.1700
Data Index: 5386987 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1725. Min Range: -8.1725
Max Act: 7.6725. Min Act: -0.1700
Data Index: 6179867 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19