Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.9290. Min Act: -0.1700
Data Index: 3927059 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.7102. Min Act: -0.1700
Data Index: 2465561 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.7102. Min Act: -0.1700
Data Index: 2465560 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.7102. Min Act: -0.1700
Data Index: 8717767 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.6165. Min Act: -0.1700
Data Index: 6869569 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.6165. Min Act: -0.1700
Data Index: 552342 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5852. Min Act: -0.1700
Data Index: 7986987 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5852. Min Act: -0.1700
Data Index: 190369 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5852. Min Act: -0.1700
Data Index: 5967214 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5852. Min Act: -0.1700
Data Index: 208853 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5540. Min Act: -0.1700
Data Index: 5422754 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5540. Min Act: -0.1700
Data Index: 8717766 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5540. Min Act: -0.1700
Data Index: 339344 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5540. Min Act: -0.1700
Data Index: 5066489 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5540. Min Act: -0.1700
Data Index: 5343203 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5227. Min Act: -0.1700
Data Index: 8459366 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5227. Min Act: -0.1700
Data Index: 2591300 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5227. Min Act: -0.1700
Data Index: 2149608 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.5227. Min Act: -0.1700
Data Index: 5524077 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9290. Min Range: -6.9290
Max Act: 6.4915. Min Act: -0.1700
Data Index: 2677189 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19