Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1408 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5831. Min Act: -0.1700
Data Index: 7284368 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5509. Min Act: -0.1700
Data Index: 5470591 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5509. Min Act: -0.1700
Data Index: 5373951 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5670. Min Act: -0.1700
Data Index: 4728671 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5509. Min Act: -0.1700
Data Index: 7025415 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5670. Min Act: -0.1700
Data Index: 333550 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5509. Min Act: -0.1700
Data Index: 5936773 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5347. Min Act: -0.1700
Data Index: 8626344 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5347. Min Act: -0.1700
Data Index: 2691760 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5186. Min Act: -0.1700
Data Index: 1641863 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5186. Min Act: -0.1700
Data Index: 8417019 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5186. Min Act: -0.1700
Data Index: 4412424 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5186. Min Act: -0.1700
Data Index: 8584912 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5347. Min Act: -0.1700
Data Index: 2841273 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5186. Min Act: -0.1700
Data Index: 4719976 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5186. Min Act: -0.1700
Data Index: 3644493 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5024. Min Act: -0.1700
Data Index: 3244590 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5186. Min Act: -0.1700
Data Index: 4558827 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5024. Min Act: -0.1700
Data Index: 3772645 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5831. Min Range: -2.5831
Max Act: 2.5024. Min Act: -0.1700
Data Index: 2157740 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19