Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.7164. Min Act: -0.1700
Data Index: 8513020 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.6227. Min Act: -0.1700
Data Index: 5344447 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.6539. Min Act: -0.1700
Data Index: 5819325 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.5914. Min Act: -0.1700
Data Index: 4954224 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.5602. Min Act: -0.1700
Data Index: 6235131 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.4664. Min Act: -0.1700
Data Index: 6673600 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.3727. Min Act: -0.1700
Data Index: 4021564 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.3414. Min Act: -0.1700
Data Index: 2043921 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.3414. Min Act: -0.1700
Data Index: 4561031 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.3102. Min Act: -0.1700
Data Index: 8138141 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.2789. Min Act: -0.1700
Data Index: 694788 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.2789. Min Act: -0.1700
Data Index: 7637936 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.2164. Min Act: -0.1700
Data Index: 4505784 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.1539. Min Act: -0.1700
Data Index: 8386343 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.1539. Min Act: -0.1700
Data Index: 787901 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.1539. Min Act: -0.1700
Data Index: 6223276 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.1227. Min Act: -0.1700
Data Index: 5868311 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.1539. Min Act: -0.1700
Data Index: 6947633 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.1227. Min Act: -0.1700
Data Index: 5260843 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7164. Min Range: -6.7164
Max Act: 6.0914. Min Act: -0.1700
Data Index: 864915 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19