Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2817 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.4063. Min Act: -0.1700
Data Index: 1195407 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.2501. Min Act: -0.1700
Data Index: 448084 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.2188. Min Act: -0.1700
Data Index: 5733993 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.1876. Min Act: -0.1700
Data Index: 2765081 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.1563. Min Act: -0.1700
Data Index: 6564172 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.1876. Min Act: -0.1700
Data Index: 1668319 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.1563. Min Act: -0.1700
Data Index: 2721048 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.1876. Min Act: -0.1700
Data Index: 3088899 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.1251. Min Act: -0.1700
Data Index: 5588030 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.0938. Min Act: -0.1700
Data Index: 846771 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.0938. Min Act: -0.1700
Data Index: 3370034 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.0938. Min Act: -0.1700
Data Index: 7150916 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.0626. Min Act: -0.1700
Data Index: 3318195 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.0626. Min Act: -0.1700
Data Index: 2370677 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.0313. Min Act: -0.1700
Data Index: 5883286 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.0313. Min Act: -0.1700
Data Index: 5885554 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4063. Min Range: -7.4063
Max Act: 7.0001. Min Act: -0.1700
Data Index: 8544505 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4063. Min Range: -7.4063
Max Act: 6.9376. Min Act: -0.1700
Data Index: 3992829 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4063. Min Range: -7.4063
Max Act: 6.9376. Min Act: -0.1700
Data Index: 3430708 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4063. Min Range: -7.4063
Max Act: 6.9376. Min Act: -0.1700
Data Index: 3194249 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19