Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5706 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.7843. Min Act: -0.1699
Data Index: 5036512 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.7218. Min Act: -0.1700
Data Index: 3347706 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.7218. Min Act: -0.1700
Data Index: 4351734 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.6905. Min Act: -0.1700
Data Index: 5081500 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.6593. Min Act: -0.1700
Data Index: 1474468 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.6593. Min Act: -0.1700
Data Index: 3942022 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.6280. Min Act: -0.1700
Data Index: 2489463 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.6280. Min Act: -0.1700
Data Index: 4307907 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5968. Min Act: -0.1700
Data Index: 1589829 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5968. Min Act: -0.1700
Data Index: 158055 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5968. Min Act: -0.1700
Data Index: 81618 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5655. Min Act: -0.1700
Data Index: 6261624 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5343. Min Act: -0.1700
Data Index: 4666485 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5343. Min Act: -0.1700
Data Index: 3431537 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5343. Min Act: -0.1700
Data Index: 2644978 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5030. Min Act: -0.1700
Data Index: 919162 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5030. Min Act: -0.1700
Data Index: 3419936 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5030. Min Act: -0.1700
Data Index: 211368 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.5030. Min Act: -0.1700
Data Index: 6902686 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7843. Min Range: -5.7843
Max Act: 5.4718. Min Act: -0.1700
Data Index: 4280777 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19