Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3808 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0929. Min Range: -3.0929
Max Act: 3.0929. Min Act: -0.1700
Data Index: 4896619 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0929. Min Range: -3.0929
Max Act: 3.0771. Min Act: -0.1700
Data Index: 3975050 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.9982. Min Act: -0.1700
Data Index: 432028 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.9824. Min Act: -0.1700
Data Index: 189254 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.9666. Min Act: -0.1700
Data Index: 5156692 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.9666. Min Act: -0.1700
Data Index: 5519914 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.9191. Min Act: -0.1700
Data Index: 3391584 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.9191. Min Act: -0.1700
Data Index: 4383687 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8874. Min Act: -0.1700
Data Index: 8796729 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8715. Min Act: -0.1700
Data Index: 932097 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8715. Min Act: -0.1700
Data Index: 1436565 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8715. Min Act: -0.1700
Data Index: 7929137 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8715. Min Act: -0.1700
Data Index: 740402 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8556. Min Act: -0.1700
Data Index: 2663112 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8715. Min Act: -0.1700
Data Index: 1574041 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8397. Min Act: -0.1700
Data Index: 6808758 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8397. Min Act: -0.1700
Data Index: 7524279 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8238. Min Act: -0.1700
Data Index: 758057 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8238. Min Act: -0.1700
Data Index: 4242614 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0929. Min Range: -3.0929
Max Act: 2.8079. Min Act: -0.1700
Data Index: 582653 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19