Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5498 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.5017. Min Act: -0.1700
Data Index: 96707 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.3142. Min Act: -0.1700
Data Index: 4971930 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.3142. Min Act: -0.1700
Data Index: 920351 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.2517. Min Act: -0.1700
Data Index: 2771937 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.3142. Min Act: -0.1700
Data Index: 6534007 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1892. Min Act: -0.1700
Data Index: 1420370 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.2517. Min Act: -0.1700
Data Index: 5422106 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1267. Min Act: -0.1700
Data Index: 7386715 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1892. Min Act: -0.1700
Data Index: 7522086 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1267. Min Act: -0.1700
Data Index: 7856597 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1892. Min Act: -0.1700
Data Index: 19734 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1267. Min Act: -0.1700
Data Index: 5207414 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1892. Min Act: -0.1700
Data Index: 4652713 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1892. Min Act: -0.1700
Data Index: 5556863 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1892. Min Act: -0.1700
Data Index: 6656042 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1267. Min Act: -0.1700
Data Index: 7180184 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1267. Min Act: -0.1700
Data Index: 6581682 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1267. Min Act: -0.1700
Data Index: 5627473 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1267. Min Act: -0.1700
Data Index: 173562 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5017. Min Range: -10.5017
Max Act: 10.1892. Min Act: -0.1700
Data Index: 2643524 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19