Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7876. Min Range: -9.7876
Max Act: 9.7876. Min Act: -0.1700
Data Index: 8645835 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7876. Min Range: -9.7876
Max Act: 9.5376. Min Act: -0.1700
Data Index: 5473907 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7876. Min Range: -9.7876
Max Act: 9.1626. Min Act: -0.1700
Data Index: 4923144 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7876. Min Range: -9.7876
Max Act: 9.1001. Min Act: -0.1700
Data Index: 714451 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7876. Min Range: -9.7876
Max Act: 9.1001. Min Act: -0.1700
Data Index: 3668617 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.9751. Min Act: -0.1700
Data Index: 4861583 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.9751. Min Act: -0.1700
Data Index: 3833380 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.9751. Min Act: -0.1700
Data Index: 7634443 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.9126. Min Act: -0.1700
Data Index: 2072408 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.9126. Min Act: -0.1700
Data Index: 1111707 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.9126. Min Act: -0.1700
Data Index: 8139575 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.9126. Min Act: -0.1700
Data Index: 2613817 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.8501. Min Act: -0.1700
Data Index: 7756718 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.8501. Min Act: -0.1700
Data Index: 6413951 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.8501. Min Act: -0.1700
Data Index: 7086488 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.8501. Min Act: -0.1700
Data Index: 4346952 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.8501. Min Act: -0.1700
Data Index: 7508244 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.7876. Min Act: -0.1700
Data Index: 6642909 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.7876. Min Act: -0.1700
Data Index: 3412648 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7876. Min Range: -9.7876
Max Act: 8.7876. Min Act: -0.1700
Data Index: 5702628 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19