Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.9304. Min Act: -0.1700
Data Index: 6785835 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.9463. Min Act: -0.1700
Data Index: 5233706 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.9146. Min Act: -0.1700
Data Index: 2670583 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8987. Min Act: -0.1700
Data Index: 7216766 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8987. Min Act: -0.1700
Data Index: 3737664 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8829. Min Act: -0.1700
Data Index: 6987802 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8829. Min Act: -0.1700
Data Index: 2478952 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8670. Min Act: -0.1700
Data Index: 4189477 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8829. Min Act: -0.1700
Data Index: 5725633 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8829. Min Act: -0.1700
Data Index: 5308508 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8829. Min Act: -0.1700
Data Index: 1917675 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8829. Min Act: -0.1700
Data Index: 1835602 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8829. Min Act: -0.1700
Data Index: 3483912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8829. Min Act: -0.1700
Data Index: 7688233 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8670. Min Act: -0.1700
Data Index: 3804045 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8670. Min Act: -0.1700
Data Index: 3992405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8670. Min Act: -0.1700
Data Index: 5590528 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8670. Min Act: -0.1700
Data Index: 6032043 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8670. Min Act: -0.1700
Data Index: 1415359 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9463. Min Range: -2.9463
Max Act: 2.8670. Min Act: -0.1700
Data Index: 6103879 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19