Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.4859. Min Act: -0.1700
Data Index: 1569011 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.4234. Min Act: -0.1700
Data Index: 1066005 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.3609. Min Act: -0.1700
Data Index: 6575100 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2984. Min Act: -0.1700
Data Index: 5304832 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2671. Min Act: -0.1700
Data Index: 2658660 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2359. Min Act: -0.1700
Data Index: 6084164 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2359. Min Act: -0.1700
Data Index: 6816237 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2359. Min Act: -0.1700
Data Index: 3287858 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2359. Min Act: -0.1700
Data Index: 3304894 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2046. Min Act: -0.1700
Data Index: 5946344 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2046. Min Act: -0.1700
Data Index: 6732197 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2046. Min Act: -0.1700
Data Index: 2384319 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2046. Min Act: -0.1700
Data Index: 1275844 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2046. Min Act: -0.1700
Data Index: 3346165 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2046. Min Act: -0.1700
Data Index: 3655313 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.2046. Min Act: -0.1700
Data Index: 1961340 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.1734. Min Act: -0.1700
Data Index: 6227086 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.1734. Min Act: -0.1700
Data Index: 8134634 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.1734. Min Act: -0.1700
Data Index: 1670687 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4859. Min Range: -4.4859
Max Act: 4.1734. Min Act: -0.1700
Data Index: 3031511 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19