Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5070 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4192. Min Range: -8.4192
Max Act: 8.4192. Min Act: -0.1700
Data Index: 2189069 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4192. Min Range: -8.4192
Max Act: 8.1692. Min Act: -0.1700
Data Index: 7219466 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.8879. Min Act: -0.1700
Data Index: 140432 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.7317. Min Act: -0.1699
Data Index: 4482385 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.6692. Min Act: -0.1700
Data Index: 4139180 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.6067. Min Act: -0.1700
Data Index: 1330418 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.6067. Min Act: -0.1700
Data Index: 6580888 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.5442. Min Act: -0.1700
Data Index: 445345 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.5442. Min Act: -0.1700
Data Index: 4327668 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.5129. Min Act: -0.1700
Data Index: 2940791 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.4504. Min Act: -0.1700
Data Index: 5018749 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.4504. Min Act: -0.1700
Data Index: 2765662 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.4192. Min Act: -0.1700
Data Index: 1513831 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.3879. Min Act: -0.1700
Data Index: 5647874 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.3879. Min Act: -0.1700
Data Index: 710737 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.3879. Min Act: -0.1700
Data Index: 3751992 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.3879. Min Act: -0.1700
Data Index: 2092812 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.3879. Min Act: -0.1700
Data Index: 6017713 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.3879. Min Act: -0.1700
Data Index: 5428104 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4192. Min Range: -8.4192
Max Act: 7.3567. Min Act: -0.1700
Data Index: 5867468 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19