Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5664 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.9949. Min Act: -0.1700
Data Index: 7012124 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.8698. Min Act: -0.1700
Data Index: 300640 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.8698. Min Act: -0.1700
Data Index: 4412130 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.8698. Min Act: -0.1700
Data Index: 8450893 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.8073. Min Act: -0.1700
Data Index: 4553493 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7760. Min Act: -0.1700
Data Index: 6099028 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7760. Min Act: -0.1700
Data Index: 5277737 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7760. Min Act: -0.1700
Data Index: 5555189 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7760. Min Act: -0.1700
Data Index: 8450894 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7760. Min Act: -0.1700
Data Index: 6163883 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7760. Min Act: -0.1700
Data Index: 2623064 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7447. Min Act: -0.1700
Data Index: 4697072 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7447. Min Act: -0.1700
Data Index: 6367223 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7447. Min Act: -0.1700
Data Index: 37358 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7447. Min Act: -0.1700
Data Index: 743802 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7134. Min Act: -0.1700
Data Index: 3507173 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7134. Min Act: -0.1700
Data Index: 6324212 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7447. Min Act: -0.1700
Data Index: 4779623 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7134. Min Act: -0.1700
Data Index: 4779622 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9949. Min Range: -3.9949
Max Act: 3.7134. Min Act: -0.1700
Data Index: 693092 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19