Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4730 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1014. Min Range: -6.1014
Max Act: 6.1014. Min Act: -0.1700
Data Index: 4654828 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.9764. Min Act: -0.1700
Data Index: 5005288 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.8514. Min Act: -0.1700
Data Index: 2689907 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7576. Min Act: -0.1700
Data Index: 2044207 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7576. Min Act: -0.1700
Data Index: 4420772 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6951. Min Act: -0.1700
Data Index: 6139788 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6951. Min Act: -0.1700
Data Index: 7713973 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6639. Min Act: -0.1700
Data Index: 703820 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6639. Min Act: -0.1700
Data Index: 635721 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6951. Min Act: -0.1700
Data Index: 5879438 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6014. Min Act: -0.1700
Data Index: 4373007 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.5701. Min Act: -0.1700
Data Index: 1346575 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.5389. Min Act: -0.1700
Data Index: 2731341 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.4764. Min Act: -0.1700
Data Index: 4608095 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.5076. Min Act: -0.1700
Data Index: 5677608 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.4451. Min Act: -0.1700
Data Index: 7558048 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.4764. Min Act: -0.1700
Data Index: 7578449 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.4764. Min Act: -0.1700
Data Index: 2112744 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.4764. Min Act: -0.1700
Data Index: 4864315 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.4764. Min Act: -0.1700
Data Index: 4875741 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19