Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2529 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1823. Min Range: -5.1823
Max Act: 5.1823. Min Act: -0.1700
Data Index: 4474083 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.8386. Min Act: -0.1700
Data Index: 3837978 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.8386. Min Act: -0.1700
Data Index: 6279010 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.8073. Min Act: -0.1700
Data Index: 7877178 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.7448. Min Act: -0.1700
Data Index: 7766233 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.7136. Min Act: -0.1700
Data Index: 2841956 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.7136. Min Act: -0.1700
Data Index: 6325476 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.7136. Min Act: -0.1700
Data Index: 8824906 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.7448. Min Act: -0.1700
Data Index: 6200365 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.7136. Min Act: -0.1700
Data Index: 6268041 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.7136. Min Act: -0.1700
Data Index: 1525908 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.6823. Min Act: -0.1700
Data Index: 2473146 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.6823. Min Act: -0.1700
Data Index: 5119075 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.6823. Min Act: -0.1700
Data Index: 779592 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.6511. Min Act: -0.1700
Data Index: 3931837 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.6823. Min Act: -0.1700
Data Index: 7948776 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.6511. Min Act: -0.1700
Data Index: 1717091 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.6823. Min Act: -0.1700
Data Index: 3215517 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.7136. Min Act: -0.1700
Data Index: 1476654 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1823. Min Range: -5.1823
Max Act: 4.6823. Min Act: -0.1700
Data Index: 5515546 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19