Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4662 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0404. Min Range: -8.0404
Max Act: 8.0404. Min Act: -0.1700
Data Index: 3981786 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.9779. Min Act: -0.1700
Data Index: 2854034 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.9779. Min Act: -0.1700
Data Index: 5565741 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.7904. Min Act: -0.1700
Data Index: 282819 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.8529. Min Act: -0.1700
Data Index: 7063664 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.7904. Min Act: -0.1700
Data Index: 3999567 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.7279. Min Act: -0.1700
Data Index: 4618655 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.6654. Min Act: -0.1700
Data Index: 3930709 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.7279. Min Act: -0.1700
Data Index: 1851712 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.6654. Min Act: -0.1700
Data Index: 25167 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.7279. Min Act: -0.1700
Data Index: 6576583 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.7279. Min Act: -0.1700
Data Index: 8222349 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.6654. Min Act: -0.1700
Data Index: 5221257 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.6654. Min Act: -0.1700
Data Index: 4555564 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.6029. Min Act: -0.1700
Data Index: 4167440 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.5717. Min Act: -0.1700
Data Index: 8482264 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.5717. Min Act: -0.1700
Data Index: 397534 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.5717. Min Act: -0.1700
Data Index: 1075724 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.5717. Min Act: -0.1700
Data Index: 5036673 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0404. Min Range: -8.0404
Max Act: 7.5717. Min Act: -0.1700
Data Index: 2604309 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19