Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1038 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.9697. Min Act: -0.1700
Data Index: 7996350 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.9385. Min Act: -0.1700
Data Index: 2801992 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.9385. Min Act: -0.1700
Data Index: 4848697 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.9385. Min Act: -0.1700
Data Index: 8173823 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.9072. Min Act: -0.1700
Data Index: 8225084 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.9072. Min Act: -0.1700
Data Index: 4739830 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.9072. Min Act: -0.1700
Data Index: 1891770 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.9385. Min Act: -0.1700
Data Index: 3856852 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8760. Min Act: -0.1700
Data Index: 6928695 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8760. Min Act: -0.1700
Data Index: 7838445 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8135. Min Act: -0.1700
Data Index: 5570875 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8447. Min Act: -0.1700
Data Index: 5777688 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8447. Min Act: -0.1700
Data Index: 3845412 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8135. Min Act: -0.1700
Data Index: 3504127 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8135. Min Act: -0.1700
Data Index: 4788060 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8447. Min Act: -0.1700
Data Index: 7725034 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8135. Min Act: -0.1700
Data Index: 1288842 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.7822. Min Act: -0.1700
Data Index: 7379538 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8135. Min Act: -0.1700
Data Index: 3037514 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9697. Min Range: -4.9697
Max Act: 4.8135. Min Act: -0.1700
Data Index: 6556799 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19