Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4776 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.5924. Min Act: -0.1700
Data Index: 3663740 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.5116. Min Act: -0.1700
Data Index: 5125972 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4792. Min Act: -0.1700
Data Index: 4739883 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4792. Min Act: -0.1700
Data Index: 5194702 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4792. Min Act: -0.1700
Data Index: 5746421 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4792. Min Act: -0.1700
Data Index: 782607 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4792. Min Act: -0.1700
Data Index: 1642100 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4630. Min Act: -0.1700
Data Index: 7955135 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4630. Min Act: -0.1700
Data Index: 5616646 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4630. Min Act: -0.1700
Data Index: 7257001 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4630. Min Act: -0.1700
Data Index: 383514 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4467. Min Act: -0.1700
Data Index: 446925 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4305. Min Act: -0.1700
Data Index: 5467011 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4467. Min Act: -0.1700
Data Index: 7615070 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4467. Min Act: -0.1700
Data Index: 3335118 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4305. Min Act: -0.1700
Data Index: 4618231 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4305. Min Act: -0.1700
Data Index: 1313537 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4305. Min Act: -0.1700
Data Index: 6737971 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4305. Min Act: -0.1700
Data Index: 2870659 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5924. Min Range: -2.5924
Max Act: 2.4305. Min Act: -0.1700
Data Index: 7083818 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19