Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3116 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1603. Min Range: -4.1603
Max Act: 4.1603. Min Act: -0.1700
Data Index: 6556703 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1603. Min Range: -4.1603
Max Act: 4.0978. Min Act: -0.1700
Data Index: 3092673 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1603. Min Range: -4.1603
Max Act: 4.0978. Min Act: -0.1700
Data Index: 6168948 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.9727. Min Act: -0.1700
Data Index: 5630552 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.9102. Min Act: -0.1700
Data Index: 4793706 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.9102. Min Act: -0.1700
Data Index: 4163753 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8789. Min Act: -0.1700
Data Index: 7940731 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8789. Min Act: -0.1700
Data Index: 3686382 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8789. Min Act: -0.1700
Data Index: 1190995 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8789. Min Act: -0.1700
Data Index: 42674 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8789. Min Act: -0.1700
Data Index: 246386 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8633. Min Act: -0.1700
Data Index: 2012646 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8477. Min Act: -0.1700
Data Index: 656853 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8789. Min Act: -0.1700
Data Index: 1303583 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8007. Min Act: -0.1700
Data Index: 4266746 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8320. Min Act: -0.1700
Data Index: 7030647 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8320. Min Act: -0.1700
Data Index: 2023191 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8164. Min Act: -0.1700
Data Index: 751042 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.8320. Min Act: -0.1700
Data Index: 4163744 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1603. Min Range: -4.1603
Max Act: 3.7851. Min Act: -0.1700
Data Index: 1982005 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19