Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1262 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.5794. Min Act: -0.1700
Data Index: 679927 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.5794. Min Act: -0.1700
Data Index: 679928 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.3606. Min Act: -0.1700
Data Index: 679930 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.1731. Min Act: -0.1700
Data Index: 87552 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.1731. Min Act: -0.1700
Data Index: 7137439 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.0169. Min Act: -0.1700
Data Index: 5402906 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.0169. Min Act: -0.1700
Data Index: 3290512 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.9856. Min Act: -0.1700
Data Index: 3290513 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.9544. Min Act: -0.1700
Data Index: 4174398 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.9231. Min Act: -0.1700
Data Index: 7137434 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.8294. Min Act: -0.1700
Data Index: 4235998 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.8606. Min Act: -0.1700
Data Index: 3179793 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.8294. Min Act: -0.1700
Data Index: 3515349 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.8294. Min Act: -0.1700
Data Index: 630837 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.8294. Min Act: -0.1700
Data Index: 3179796 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.8294. Min Act: -0.1700
Data Index: 646856 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.7669. Min Act: -0.1700
Data Index: 2779639 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.7044. Min Act: -0.1700
Data Index: 2750995 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.7669. Min Act: -0.1700
Data Index: 4236001 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5794. Min Range: -7.5794
Max Act: 6.7044. Min Act: -0.1700
Data Index: 4235997 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19