Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 729 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.8851. Min Act: -0.1700
Data Index: 8232176 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.8539. Min Act: -0.1700
Data Index: 4850525 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.8226. Min Act: -0.1700
Data Index: 7751568 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.8226. Min Act: -0.1700
Data Index: 3048256 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.7914. Min Act: -0.1700
Data Index: 6125452 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.7601. Min Act: -0.1700
Data Index: 8287992 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.7601. Min Act: -0.1700
Data Index: 8288009 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.7289. Min Act: -0.1700
Data Index: 3273528 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.7289. Min Act: -0.1700
Data Index: 2618496 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.7289. Min Act: -0.1700
Data Index: 554261 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.6976. Min Act: -0.1700
Data Index: 2661311 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.7289. Min Act: -0.1700
Data Index: 4816353 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.6664. Min Act: -0.1700
Data Index: 2797061 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.6351. Min Act: -0.1700
Data Index: 4710230 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.6351. Min Act: -0.1700
Data Index: 3575988 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.6351. Min Act: -0.1700
Data Index: 1336977 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.6351. Min Act: -0.1700
Data Index: 472971 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.6038. Min Act: -0.1700
Data Index: 4758721 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.6038. Min Act: -0.1700
Data Index: 3714998 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8851. Min Range: -4.8851
Max Act: 4.5726. Min Act: -0.1700
Data Index: 674742 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19