Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.4173. Min Act: -0.1700
Data Index: 6966887 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.3861. Min Act: -0.1700
Data Index: 7998679 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.3861. Min Act: -0.1700
Data Index: 2997751 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.3548. Min Act: -0.1700
Data Index: 2997748 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.2923. Min Act: -0.1700
Data Index: 1166008 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.2923. Min Act: -0.1700
Data Index: 2997750 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.2611. Min Act: -0.1700
Data Index: 3083791 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.2298. Min Act: -0.1700
Data Index: 2997746 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.2298. Min Act: -0.1700
Data Index: 1166004 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1985. Min Act: -0.1700
Data Index: 7379455 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1985. Min Act: -0.1700
Data Index: 7124126 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1985. Min Act: -0.1700
Data Index: 6966888 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1985. Min Act: -0.1700
Data Index: 2997743 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1985. Min Act: -0.1700
Data Index: 2997747 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1985. Min Act: -0.1700
Data Index: 5180493 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1673. Min Act: -0.1700
Data Index: 5715653 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1673. Min Act: -0.1700
Data Index: 6375863 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1360. Min Act: -0.1700
Data Index: 2997749 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1360. Min Act: -0.1700
Data Index: 3828337 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4173. Min Range: -4.4173
Max Act: 4.1360. Min Act: -0.1700
Data Index: 5715658 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19