Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.8719. Min Act: -0.1700
Data Index: 5080758 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.8719. Min Act: -0.1700
Data Index: 7839281 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.8406. Min Act: -0.1700
Data Index: 2849653 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.8406. Min Act: -0.1700
Data Index: 3241276 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.8094. Min Act: -0.1700
Data Index: 5367697 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.7781. Min Act: -0.1700
Data Index: 5861591 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.7781. Min Act: -0.1700
Data Index: 4603891 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.7781. Min Act: -0.1700
Data Index: 3849699 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.7469. Min Act: -0.1700
Data Index: 485888 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.7156. Min Act: -0.1700
Data Index: 1171900 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.7156. Min Act: -0.1700
Data Index: 5504860 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.7156. Min Act: -0.1700
Data Index: 5547005 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.7156. Min Act: -0.1700
Data Index: 137573 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.6531. Min Act: -0.1700
Data Index: 5367696 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.6531. Min Act: -0.1700
Data Index: 1489626 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.7156. Min Act: -0.1700
Data Index: 4868072 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.6844. Min Act: -0.1700
Data Index: 103339 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.6531. Min Act: -0.1700
Data Index: 1304711 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.6531. Min Act: -0.1700
Data Index: 792045 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8719. Min Range: -5.8719
Max Act: 5.6531. Min Act: -0.1700
Data Index: 196842 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19