Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.7171. Min Act: -0.1700
Data Index: 7930634 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.7171. Min Act: -0.1700
Data Index: 5848047 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.6859. Min Act: -0.1700
Data Index: 2376497 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.6546. Min Act: -0.1700
Data Index: 8238976 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.5921. Min Act: -0.1700
Data Index: 6121372 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.5296. Min Act: -0.1700
Data Index: 5677732 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.5296. Min Act: -0.1700
Data Index: 3349657 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4984. Min Act: -0.1700
Data Index: 8087506 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4984. Min Act: -0.1700
Data Index: 1556805 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4984. Min Act: -0.1700
Data Index: 1186982 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4984. Min Act: -0.1700
Data Index: 3623844 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4671. Min Act: -0.1700
Data Index: 7520526 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4671. Min Act: -0.1700
Data Index: 7930633 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4671. Min Act: -0.1700
Data Index: 429483 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4671. Min Act: -0.1700
Data Index: 773600 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4671. Min Act: -0.1700
Data Index: 7180182 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4046. Min Act: -0.1700
Data Index: 5772051 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4359. Min Act: -0.1700
Data Index: 1556804 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4046. Min Act: -0.1700
Data Index: 1056659 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7171. Min Range: -6.7171
Max Act: 6.4046. Min Act: -0.1700
Data Index: 5677729 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19