Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3729 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.7081. Min Act: -0.1700
Data Index: 519575 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.6769. Min Act: -0.1700
Data Index: 4705 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.6456. Min Act: -0.1700
Data Index: 5627044 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.4894. Min Act: -0.1700
Data Index: 2866801 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3019. Min Act: -0.1700
Data Index: 7203000 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3019. Min Act: -0.1700
Data Index: 7273148 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3019. Min Act: -0.1700
Data Index: 7469867 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2706. Min Act: -0.1700
Data Index: 6350987 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2394. Min Act: -0.1700
Data Index: 4488946 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2394. Min Act: -0.1700
Data Index: 2990081 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2081. Min Act: -0.1700
Data Index: 2140613 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2394. Min Act: -0.1700
Data Index: 6919827 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.1769. Min Act: -0.1700
Data Index: 2762821 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.1769. Min Act: -0.1700
Data Index: 5418185 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.1769. Min Act: -0.1700
Data Index: 4776771 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.1769. Min Act: -0.1700
Data Index: 3230637 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.1769. Min Act: -0.1700
Data Index: 6079912 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.1769. Min Act: -0.1700
Data Index: 2141372 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.1769. Min Act: -0.1700
Data Index: 1403625 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.1456. Min Act: -0.1700
Data Index: 2930881 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19