Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.4130. Min Act: -0.1700
Data Index: 3876612 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.3817. Min Act: -0.1700
Data Index: 7133649 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.3505. Min Act: -0.1700
Data Index: 699307 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.2567. Min Act: -0.1700
Data Index: 1135507 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.2567. Min Act: -0.1700
Data Index: 6830936 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.2567. Min Act: -0.1700
Data Index: 389379 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.2255. Min Act: -0.1700
Data Index: 7953592 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1942. Min Act: -0.1700
Data Index: 1654272 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1630. Min Act: -0.1700
Data Index: 3322805 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1630. Min Act: -0.1700
Data Index: 5233015 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1317. Min Act: -0.1700
Data Index: 159604 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1630. Min Act: -0.1700
Data Index: 2589637 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1317. Min Act: -0.1700
Data Index: 1422764 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1630. Min Act: -0.1700
Data Index: 2158812 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1005. Min Act: -0.1700
Data Index: 4031859 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1005. Min Act: -0.1700
Data Index: 3142680 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1317. Min Act: -0.1700
Data Index: 5262077 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.1005. Min Act: -0.1700
Data Index: 2149859 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.0692. Min Act: -0.1700
Data Index: 6218792 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4130. Min Range: -5.4130
Max Act: 5.0692. Min Act: -0.1700
Data Index: 5960090 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19