Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1515 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.8731. Min Act: -0.1700
Data Index: 360083 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.8419. Min Act: -0.1700
Data Index: 6168001 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.8419. Min Act: -0.1700
Data Index: 5423545 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.8419. Min Act: -0.1700
Data Index: 2168356 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7793. Min Act: -0.1700
Data Index: 174828 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7793. Min Act: -0.1700
Data Index: 704513 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7324. Min Act: -0.1700
Data Index: 6110906 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7637. Min Act: -0.1700
Data Index: 8539172 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7637. Min Act: -0.1700
Data Index: 5031725 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7637. Min Act: -0.1700
Data Index: 3025512 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7167. Min Act: -0.1700
Data Index: 1841493 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7324. Min Act: -0.1700
Data Index: 967350 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7637. Min Act: -0.1700
Data Index: 3520719 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7324. Min Act: -0.1700
Data Index: 688973 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7167. Min Act: -0.1700
Data Index: 7126902 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7011. Min Act: -0.1700
Data Index: 8330706 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7011. Min Act: -0.1700
Data Index: 1007666 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7011. Min Act: -0.1700
Data Index: 5182401 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.7011. Min Act: -0.1700
Data Index: 5549635 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8731. Min Range: -3.8731
Max Act: 3.6698. Min Act: -0.1700
Data Index: 2341942 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19