Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 723 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.9537. Min Act: -0.1700
Data Index: 145635 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.9378. Min Act: -0.1700
Data Index: 923240 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8903. Min Act: -0.1700
Data Index: 4260051 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8744. Min Act: -0.1700
Data Index: 4837445 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8744. Min Act: -0.1700
Data Index: 2074777 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8585. Min Act: -0.1700
Data Index: 7667878 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8585. Min Act: -0.1700
Data Index: 2132982 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8426. Min Act: -0.1700
Data Index: 1126566 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8585. Min Act: -0.1700
Data Index: 5088294 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8426. Min Act: -0.1700
Data Index: 3790588 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8426. Min Act: -0.1700
Data Index: 5096388 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8426. Min Act: -0.1700
Data Index: 7656859 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8267. Min Act: -0.1700
Data Index: 6896685 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8267. Min Act: -0.1700
Data Index: 7667884 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8108. Min Act: -0.1700
Data Index: 6692401 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8108. Min Act: -0.1700
Data Index: 6459932 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8108. Min Act: -0.1700
Data Index: 2434703 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8108. Min Act: -0.1700
Data Index: 4260053 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.8108. Min Act: -0.1700
Data Index: 923231 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9537. Min Range: -2.9537
Max Act: 2.7949. Min Act: -0.1700
Data Index: 7255736 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19