Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.8671. Min Act: -0.1695
Data Index: 3142115 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.8358. Min Act: -0.1700
Data Index: 8534000 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7733. Min Act: -0.1694
Data Index: 554418 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7733. Min Act: -0.1700
Data Index: 3153066 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7733. Min Act: -0.1698
Data Index: 6990924 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7733. Min Act: -0.1700
Data Index: 1948576 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7733. Min Act: -0.1700
Data Index: 5348912 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7421. Min Act: -0.1699
Data Index: 6596755 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7421. Min Act: -0.1700
Data Index: 1791791 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7421. Min Act: -0.1700
Data Index: 2991375 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7421. Min Act: -0.1700
Data Index: 7755132 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7421. Min Act: -0.1700
Data Index: 3746764 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7421. Min Act: -0.1700
Data Index: 183952 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7421. Min Act: -0.1700
Data Index: 7542616 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7421. Min Act: -0.1700
Data Index: 700239 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7108. Min Act: -0.1700
Data Index: 4853787 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7108. Min Act: -0.1700
Data Index: 104998 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7108. Min Act: -0.1700
Data Index: 1768075 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7108. Min Act: -0.1700
Data Index: 6267687 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8671. Min Range: -5.8671
Max Act: 5.7108. Min Act: -0.1700
Data Index: 6548338 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19