Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1564 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.9973. Min Act: -0.1700
Data Index: 6226866 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.9973. Min Act: -0.1700
Data Index: 8564357 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.9661. Min Act: -0.1700
Data Index: 5497406 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.9035. Min Act: -0.1700
Data Index: 8708556 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.9035. Min Act: -0.1700
Data Index: 3730900 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8723. Min Act: -0.1700
Data Index: 8083951 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8723. Min Act: -0.1700
Data Index: 1502788 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8723. Min Act: -0.1700
Data Index: 7997351 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8723. Min Act: -0.1700
Data Index: 3035495 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8097. Min Act: -0.1700
Data Index: 4421974 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8097. Min Act: -0.1700
Data Index: 2596385 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8410. Min Act: -0.1700
Data Index: 8708554 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8097. Min Act: -0.1700
Data Index: 6219627 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8723. Min Act: -0.1700
Data Index: 3867484 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.7785. Min Act: -0.1700
Data Index: 752793 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8097. Min Act: -0.1700
Data Index: 3452514 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8097. Min Act: -0.1700
Data Index: 6189810 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8097. Min Act: -0.1700
Data Index: 4886114 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8097. Min Act: -0.1700
Data Index: 6079496 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9973. Min Range: -3.9973
Max Act: 3.8097. Min Act: -0.1700
Data Index: 5832142 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19