Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4823 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3067. Min Range: -9.3067
Max Act: 9.3067. Min Act: -0.1700
Data Index: 7830760 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3067. Min Range: -9.3067
Max Act: 9.2442. Min Act: -0.1700
Data Index: 3856251 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3067. Min Range: -9.3067
Max Act: 9.1817. Min Act: -0.1700
Data Index: 6784721 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3067. Min Range: -9.3067
Max Act: 9.1817. Min Act: -0.1700
Data Index: 6408256 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3067. Min Range: -9.3067
Max Act: 9.0567. Min Act: -0.1700
Data Index: 1232403 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3067. Min Range: -9.3067
Max Act: 9.0567. Min Act: -0.1700
Data Index: 8279322 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.9942. Min Act: -0.1700
Data Index: 1421180 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.9942. Min Act: -0.1700
Data Index: 6077788 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.8692. Min Act: -0.1700
Data Index: 6806965 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.8067. Min Act: -0.1700
Data Index: 7421485 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.8067. Min Act: -0.1700
Data Index: 6534699 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.8067. Min Act: -0.1700
Data Index: 6898833 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 5415676 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 5176186 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 5757614 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 1423210 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 3942879 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 6836998 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.6192. Min Act: -0.1700
Data Index: 1919699 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3067. Min Range: -9.3067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 4116425 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19