Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3989 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0831. Min Range: -8.0831
Max Act: 8.0831. Min Act: -0.1700
Data Index: 7978480 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.8331. Min Act: -0.1700
Data Index: 8200971 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.8331. Min Act: -0.1700
Data Index: 3107034 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.8331. Min Act: -0.1700
Data Index: 322225 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.8331. Min Act: -0.1700
Data Index: 2527827 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.7706. Min Act: -0.1700
Data Index: 5429777 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.7081. Min Act: -0.1700
Data Index: 7198789 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.7706. Min Act: -0.1700
Data Index: 7601974 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.7081. Min Act: -0.1700
Data Index: 5104063 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.7081. Min Act: -0.1700
Data Index: 1074796 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.6456. Min Act: -0.1700
Data Index: 4769462 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.5831. Min Act: -0.1700
Data Index: 5674037 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.5831. Min Act: -0.1700
Data Index: 7199678 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.5831. Min Act: -0.1700
Data Index: 3640329 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.5206. Min Act: -0.1700
Data Index: 3247033 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.5831. Min Act: -0.1700
Data Index: 6670975 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.5831. Min Act: -0.1700
Data Index: 7559597 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.5831. Min Act: -0.1700
Data Index: 7734484 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.5831. Min Act: -0.1700
Data Index: 5609 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0831. Min Range: -8.0831
Max Act: 7.5831. Min Act: -0.1700
Data Index: 6411304 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19