Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.9624. Min Act: -0.1700
Data Index: 1019391 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.8687. Min Act: -0.1700
Data Index: 1313414 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.8687. Min Act: -0.1700
Data Index: 1608377 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.8062. Min Act: -0.1700
Data Index: 6484141 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.8062. Min Act: -0.1700
Data Index: 8575284 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.7749. Min Act: -0.1700
Data Index: 967154 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.7437. Min Act: -0.1700
Data Index: 1599861 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.7437. Min Act: -0.1700
Data Index: 8246728 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.7124. Min Act: -0.1700
Data Index: 5412468 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.7124. Min Act: -0.1700
Data Index: 5134610 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.7124. Min Act: -0.1700
Data Index: 1055058 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.7124. Min Act: -0.1700
Data Index: 887617 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.6812. Min Act: -0.1700
Data Index: 4779898 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.6812. Min Act: -0.1700
Data Index: 5053330 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.6812. Min Act: -0.1700
Data Index: 4871800 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.6812. Min Act: -0.1700
Data Index: 1880456 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.6812. Min Act: -0.1700
Data Index: 5396265 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.6499. Min Act: -0.1700
Data Index: 2594740 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.6499. Min Act: -0.1700
Data Index: 6515855 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9624. Min Range: -4.9624
Max Act: 4.6499. Min Act: -0.1700
Data Index: 7863885 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19