Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.9500. Min Act: -0.1700
Data Index: 4243889 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.9500. Min Act: -0.1700
Data Index: 2120121 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.8250. Min Act: -0.1700
Data Index: 8062892 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.7625. Min Act: -0.1700
Data Index: 2395235 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.7625. Min Act: -0.1700
Data Index: 1726526 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.7625. Min Act: -0.1700
Data Index: 781775 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.7000. Min Act: -0.1700
Data Index: 8013959 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.6688. Min Act: -0.1700
Data Index: 6198566 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.6688. Min Act: -0.1700
Data Index: 1212152 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.6375. Min Act: -0.1700
Data Index: 6725694 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.6063. Min Act: -0.1700
Data Index: 708481 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.4500. Min Act: -0.1700
Data Index: 3459791 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.3875. Min Act: -0.1700
Data Index: 41010 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.3563. Min Act: -0.1700
Data Index: 3958223 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.3875. Min Act: -0.1700
Data Index: 7628812 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.3875. Min Act: -0.1700
Data Index: 2599130 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.3563. Min Act: -0.1700
Data Index: 8423622 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.3563. Min Act: -0.1700
Data Index: 6188802 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.2938. Min Act: -0.1700
Data Index: 838966 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9500. Min Range: -7.9500
Max Act: 7.2938. Min Act: -0.1700
Data Index: 7058115 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19