Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0301. Min Range: -11.0301
Max Act: 11.0301. Min Act: -0.1700
Data Index: 4945366 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.9051. Min Act: -0.1700
Data Index: 8140623 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.6551. Min Act: -0.1700
Data Index: 8121329 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.6551. Min Act: -0.1700
Data Index: 760467 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.7176. Min Act: -0.1700
Data Index: 4357386 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.5926. Min Act: -0.1700
Data Index: 6197809 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.4676. Min Act: -0.1700
Data Index: 1656084 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.4676. Min Act: -0.1700
Data Index: 3831060 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.4051. Min Act: -0.1700
Data Index: 6372714 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.4051. Min Act: -0.1700
Data Index: 1532758 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.4051. Min Act: -0.1700
Data Index: 658929 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.4051. Min Act: -0.1700
Data Index: 472091 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.4051. Min Act: -0.1700
Data Index: 1939764 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.3426. Min Act: -0.1700
Data Index: 5904601 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.2801. Min Act: -0.1700
Data Index: 1028147 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.3426. Min Act: -0.1700
Data Index: 1647107 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.3426. Min Act: -0.1700
Data Index: 1478210 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.2801. Min Act: -0.1700
Data Index: 1874279 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.2801. Min Act: -0.1700
Data Index: 8614083 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0301. Min Range: -11.0301
Max Act: 10.2176. Min Act: -0.1700
Data Index: 1336312 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19