Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2501. Min Range: -7.2501
Max Act: 7.2501. Min Act: -0.1700
Data Index: 7319927 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2501. Min Range: -7.2501
Max Act: 7.0938. Min Act: -0.1700
Data Index: 1694591 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2501. Min Range: -7.2501
Max Act: 7.0626. Min Act: -0.1700
Data Index: 989409 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2501. Min Range: -7.2501
Max Act: 7.0313. Min Act: -0.1700
Data Index: 7002892 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2501. Min Range: -7.2501
Max Act: 7.0313. Min Act: -0.1700
Data Index: 6459804 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2501. Min Range: -7.2501
Max Act: 7.0313. Min Act: -0.1700
Data Index: 1620712 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.9688. Min Act: -0.1700
Data Index: 1838553 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.9376. Min Act: -0.1700
Data Index: 3913651 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.9063. Min Act: -0.1700
Data Index: 4775399 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.8438. Min Act: -0.1700
Data Index: 8200446 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.8126. Min Act: -0.1700
Data Index: 3670585 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.8126. Min Act: -0.1700
Data Index: 8403976 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.8126. Min Act: -0.1700
Data Index: 7247975 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.8126. Min Act: -0.1700
Data Index: 5526461 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.8126. Min Act: -0.1700
Data Index: 5689841 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.7813. Min Act: -0.1700
Data Index: 6418645 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.7501. Min Act: -0.1700
Data Index: 7406346 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.7501. Min Act: -0.1700
Data Index: 8756742 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.7188. Min Act: -0.1700
Data Index: 7310080 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2501. Min Range: -7.2501
Max Act: 6.7188. Min Act: -0.1700
Data Index: 3828339 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19