Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1880 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 6351064 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 7145960 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2554. Min Act: -0.1700
Data Index: 4140256 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 5929299 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2554. Min Act: -0.1700
Data Index: 3144966 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1617. Min Act: -0.1700
Data Index: 1078494 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1929. Min Act: -0.1700
Data Index: 6192736 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1617. Min Act: -0.1700
Data Index: 4855970 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1304. Min Act: -0.1700
Data Index: 8041681 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1304. Min Act: -0.1700
Data Index: 3515631 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1304. Min Act: -0.1700
Data Index: 8183848 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1304. Min Act: -0.1700
Data Index: 7145961 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 6258504 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 1505359 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 2626299 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 6288366 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 1602146 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 8112290 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0054. Min Act: -0.1700
Data Index: 6258499 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0367. Min Act: -0.1700
Data Index: 5159552 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19