Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.7021. Min Act: -0.1700
Data Index: 5032609 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6865. Min Act: -0.1700
Data Index: 1828445 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.7021. Min Act: -0.1700
Data Index: 8046428 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6865. Min Act: -0.1700
Data Index: 2649887 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6239. Min Act: -0.1700
Data Index: 5465374 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6239. Min Act: -0.1700
Data Index: 873330 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6239. Min Act: -0.1700
Data Index: 1759356 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6239. Min Act: -0.1700
Data Index: 921314 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6239. Min Act: -0.1700
Data Index: 997365 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6082. Min Act: -0.1700
Data Index: 1033392 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6082. Min Act: -0.1700
Data Index: 6444473 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6082. Min Act: -0.1700
Data Index: 7720857 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6082. Min Act: -0.1700
Data Index: 1981735 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.5926. Min Act: -0.1700
Data Index: 660136 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6082. Min Act: -0.1700
Data Index: 949810 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6239. Min Act: -0.1700
Data Index: 7187871 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6082. Min Act: -0.1700
Data Index: 7089843 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6082. Min Act: -0.1700
Data Index: 3460034 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.5926. Min Act: -0.1700
Data Index: 1908446 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7021. Min Range: -3.7021
Max Act: 3.6082. Min Act: -0.1700
Data Index: 3835972 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19