Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1878 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.6098. Min Act: -0.1700
Data Index: 4201854 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.6098. Min Act: -0.1700
Data Index: 2715126 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5941. Min Act: -0.1700
Data Index: 1270619 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5785. Min Act: -0.1700
Data Index: 491334 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5785. Min Act: -0.1700
Data Index: 4222542 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5785. Min Act: -0.1700
Data Index: 5399250 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5472. Min Act: -0.1700
Data Index: 3995073 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5472. Min Act: -0.1700
Data Index: 3261322 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5472. Min Act: -0.1700
Data Index: 1526321 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5315. Min Act: -0.1700
Data Index: 4911616 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5472. Min Act: -0.1700
Data Index: 3910071 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5159. Min Act: -0.1700
Data Index: 8814949 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5159. Min Act: -0.1700
Data Index: 6195574 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5315. Min Act: -0.1700
Data Index: 6900636 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5159. Min Act: -0.1700
Data Index: 6434047 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5472. Min Act: -0.1700
Data Index: 7452373 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5159. Min Act: -0.1700
Data Index: 7774072 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5315. Min Act: -0.1700
Data Index: 3599332 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5159. Min Act: -0.1700
Data Index: 2452296 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6098. Min Range: -3.6098
Max Act: 3.5159. Min Act: -0.1700
Data Index: 4104069 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19