Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.3616. Min Act: -0.1700
Data Index: 1250440 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.3459. Min Act: -0.1700
Data Index: 8357697 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.3302. Min Act: -0.1700
Data Index: 2360427 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2831. Min Act: -0.1700
Data Index: 2753759 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2831. Min Act: -0.1700
Data Index: 7680441 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2517. Min Act: -0.1700
Data Index: 2391624 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2203. Min Act: -0.1700
Data Index: 1201271 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2360. Min Act: -0.1700
Data Index: 4366850 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2360. Min Act: -0.1700
Data Index: 3642797 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2203. Min Act: -0.1700
Data Index: 6395293 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2045. Min Act: -0.1700
Data Index: 920825 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2045. Min Act: -0.1700
Data Index: 7345977 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.2045. Min Act: -0.1700
Data Index: 5310250 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.1888. Min Act: -0.1700
Data Index: 56428 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.1731. Min Act: -0.1700
Data Index: 2999862 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.1731. Min Act: -0.1700
Data Index: 647505 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.1731. Min Act: -0.1700
Data Index: 6091277 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.1573. Min Act: -0.1700
Data Index: 3528535 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.1573. Min Act: -0.1700
Data Index: 1038148 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3616. Min Range: -3.3616
Max Act: 3.1416. Min Act: -0.1700
Data Index: 4642952 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19