Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5193. Min Range: -8.5193
Max Act: 8.5193. Min Act: -0.1700
Data Index: 5019240 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5193. Min Range: -8.5193
Max Act: 8.2693. Min Act: -0.1700
Data Index: 7373777 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5193. Min Range: -8.5193
Max Act: 8.2068. Min Act: -0.1700
Data Index: 175978 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5193. Min Range: -8.5193
Max Act: 8.0818. Min Act: -0.1700
Data Index: 3240425 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.9568. Min Act: -0.1700
Data Index: 8654814 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.9568. Min Act: -0.1700
Data Index: 2929597 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.8630. Min Act: -0.1700
Data Index: 6005185 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.8943. Min Act: -0.1700
Data Index: 7803333 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.8630. Min Act: -0.1700
Data Index: 2249313 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.8630. Min Act: -0.1700
Data Index: 1812788 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.8630. Min Act: -0.1700
Data Index: 2124215 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.8005. Min Act: -0.1700
Data Index: 4105192 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.8005. Min Act: -0.1700
Data Index: 1161179 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.8318. Min Act: -0.1700
Data Index: 1519427 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.8005. Min Act: -0.1700
Data Index: 27048 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.7380. Min Act: -0.1700
Data Index: 963559 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.7693. Min Act: -0.1700
Data Index: 5377916 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.7693. Min Act: -0.1700
Data Index: 2647069 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.7693. Min Act: -0.1700
Data Index: 7076631 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5193. Min Range: -8.5193
Max Act: 7.7380. Min Act: -0.1700
Data Index: 7872550 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19