Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3846 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.7541. Min Act: -0.1700
Data Index: 826598 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.7854. Min Act: -0.1700
Data Index: 6833992 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.5977. Min Act: -0.1700
Data Index: 1983514 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.5820. Min Act: -0.1700
Data Index: 8022536 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.5820. Min Act: -0.1700
Data Index: 124426 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.5507. Min Act: -0.1700
Data Index: 3501152 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.5194. Min Act: -0.1700
Data Index: 4486717 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.5037. Min Act: -0.1700
Data Index: 80915 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.5194. Min Act: -0.1700
Data Index: 8241373 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.4724. Min Act: -0.1700
Data Index: 2641903 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.4254. Min Act: -0.1700
Data Index: 8564696 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.4567. Min Act: -0.1700
Data Index: 1139626 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.4254. Min Act: -0.1700
Data Index: 5080509 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.4411. Min Act: -0.1700
Data Index: 3069358 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.4097. Min Act: -0.1700
Data Index: 6591698 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.3784. Min Act: -0.1700
Data Index: 5556165 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.3156. Min Act: -0.1700
Data Index: 6833991 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.3470. Min Act: -0.1700
Data Index: 4880994 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.3470. Min Act: -0.1700
Data Index: 921711 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7854. Min Range: -3.7854
Max Act: 3.3470. Min Act: -0.1700
Data Index: 3741100 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19