Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4968 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.6284. Min Act: -0.1700
Data Index: 3978461 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.4722. Min Act: -0.1700
Data Index: 2851331 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.5034. Min Act: -0.1700
Data Index: 4134943 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.4409. Min Act: -0.1700
Data Index: 985425 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.4096. Min Act: -0.1700
Data Index: 4367445 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.4096. Min Act: -0.1700
Data Index: 1286946 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.4096. Min Act: -0.1700
Data Index: 5285976 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3784. Min Act: -0.1700
Data Index: 5717894 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.4096. Min Act: -0.1700
Data Index: 5198568 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.4096. Min Act: -0.1700
Data Index: 330726 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3784. Min Act: -0.1700
Data Index: 5213827 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3471. Min Act: -0.1700
Data Index: 625955 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3471. Min Act: -0.1700
Data Index: 2835982 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3159. Min Act: -0.1700
Data Index: 1982572 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3159. Min Act: -0.1700
Data Index: 824792 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3159. Min Act: -0.1700
Data Index: 2289783 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3471. Min Act: -0.1700
Data Index: 2886801 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3471. Min Act: -0.1700
Data Index: 7043565 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3471. Min Act: -0.1700
Data Index: 1082679 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6284. Min Range: -4.6284
Max Act: 4.3471. Min Act: -0.1700
Data Index: 7636007 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19