Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2484 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.9453. Min Act: -0.1700
Data Index: 545673 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.6641. Min Act: -0.1700
Data Index: 979378 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.3203. Min Act: -0.1700
Data Index: 26501 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.3516. Min Act: -0.1700
Data Index: 1993039 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.2891. Min Act: -0.1700
Data Index: 5604997 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.2891. Min Act: -0.1700
Data Index: 8829446 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.2266. Min Act: -0.1700
Data Index: 6503044 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.2578. Min Act: -0.1700
Data Index: 6658522 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.2266. Min Act: -0.1700
Data Index: 3523296 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1953. Min Act: -0.1700
Data Index: 8040705 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1953. Min Act: -0.1700
Data Index: 4873941 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1328. Min Act: -0.1700
Data Index: 8437696 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1641. Min Act: -0.1700
Data Index: 4421212 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1641. Min Act: -0.1700
Data Index: 256633 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1328. Min Act: -0.1700
Data Index: 7884197 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1328. Min Act: -0.1700
Data Index: 7937167 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1328. Min Act: -0.1700
Data Index: 5703293 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1016. Min Act: -0.1700
Data Index: 4170701 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.0703. Min Act: -0.1700
Data Index: 5429963 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9453. Min Range: -6.9453
Max Act: 6.1328. Min Act: -0.1700
Data Index: 4701301 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19