Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5839 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.4007. Min Act: -0.1700
Data Index: 760986 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.3655. Min Act: -0.1698
Data Index: 6187341 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.3655. Min Act: -0.1692
Data Index: 3959393 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.3126. Min Act: -0.1700
Data Index: 3812227 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.3126. Min Act: -0.1700
Data Index: 1609535 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.2773. Min Act: -0.1700
Data Index: 6803075 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.2420. Min Act: -0.1700
Data Index: 4865074 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.2244. Min Act: -0.1700
Data Index: 7788387 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.2068. Min Act: -0.1700
Data Index: 8297648 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1892. Min Act: -0.1700
Data Index: 8610426 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1892. Min Act: -0.1700
Data Index: 1115312 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1892. Min Act: -0.1700
Data Index: 8832530 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1892. Min Act: -0.1700
Data Index: 4339418 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1892. Min Act: -0.1700
Data Index: 7726926 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1716. Min Act: -0.1700
Data Index: 7671326 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1892. Min Act: -0.1700
Data Index: 7531299 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1716. Min Act: -0.1700
Data Index: 3294203 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1716. Min Act: -0.1700
Data Index: 1751563 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1716. Min Act: -0.1700
Data Index: 1941094 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4007. Min Range: -1.4007
Max Act: 1.1716. Min Act: -0.1700
Data Index: 5169598 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19