Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2442 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.9497. Min Act: -0.1700
Data Index: 4155801 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.8247. Min Act: -0.1700
Data Index: 7728653 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.6997. Min Act: -0.1700
Data Index: 7629889 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.6997. Min Act: -0.1700
Data Index: 7406672 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.6997. Min Act: -0.1700
Data Index: 2905469 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.6997. Min Act: -0.1700
Data Index: 5243168 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.6372. Min Act: -0.1700
Data Index: 984132 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.6372. Min Act: -0.1700
Data Index: 336724 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.6372. Min Act: -0.1700
Data Index: 5687473 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.6372. Min Act: -0.1700
Data Index: 2745376 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5747. Min Act: -0.1700
Data Index: 1596520 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5747. Min Act: -0.1700
Data Index: 1619558 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5747. Min Act: -0.1700
Data Index: 960809 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5747. Min Act: -0.1700
Data Index: 6571287 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5747. Min Act: -0.1700
Data Index: 8170711 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5122. Min Act: -0.1700
Data Index: 7509929 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5122. Min Act: -0.1700
Data Index: 4562048 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5122. Min Act: -0.1700
Data Index: 3435217 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5122. Min Act: -0.1700
Data Index: 6860515 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9497. Min Range: -7.9497
Max Act: 7.5122. Min Act: -0.1700
Data Index: 1367888 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19