Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1043 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1606. Min Range: -2.1606
Max Act: 2.1606. Min Act: -0.1697
Data Index: 1299811 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.9759. Min Act: -0.1698
Data Index: 6064388 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.8909. Min Act: -0.1700
Data Index: 485206 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.8738. Min Act: -0.1700
Data Index: 1713886 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.8396. Min Act: -0.1700
Data Index: 1668000 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.8052. Min Act: -0.1700
Data Index: 6591064 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.8224. Min Act: -0.1700
Data Index: 8435895 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.8224. Min Act: -0.1700
Data Index: 3340342 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.7880. Min Act: -0.1696
Data Index: 1569015 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.7880. Min Act: -0.1679
Data Index: 7335316 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.7708. Min Act: -0.1521
Data Index: 5801009 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.7708. Min Act: -0.1700
Data Index: 943908 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.7362. Min Act: -0.1694
Data Index: 7752331 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.7189. Min Act: -0.1700
Data Index: 4755405 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.7016. Min Act: -0.1688
Data Index: 4922617 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.7189. Min Act: -0.1700
Data Index: 7896385 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.7189. Min Act: -0.1700
Data Index: 8804943 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.6842. Min Act: -0.1700
Data Index: 1877821 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.6842. Min Act: -0.1700
Data Index: 2062599 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1606. Min Range: -2.1606
Max Act: 1.6669. Min Act: -0.1700
Data Index: 6681490 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19