Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1039 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1014. Min Range: -6.1014
Max Act: 6.1014. Min Act: -0.1700
Data Index: 8410837 (Open Web Text)
Max Activating Token Index: 197
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: 7857183 (Open Web Text)
Max Activating Token Index: 251
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: 1036723 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.8826. Min Act: -0.1700
Data Index: 5527954 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.8201. Min Act: -0.1700
Data Index: 1415753 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.8514. Min Act: -0.1700
Data Index: 6833860 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7889. Min Act: -0.1700
Data Index: 7911991 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.8201. Min Act: -0.1700
Data Index: 3051170 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7576. Min Act: -0.1700
Data Index: 1872703 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7576. Min Act: -0.1700
Data Index: 5813485 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7576. Min Act: -0.1700
Data Index: 366260 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7264. Min Act: -0.1700
Data Index: 4805507 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7264. Min Act: -0.1700
Data Index: 7914317 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7264. Min Act: -0.1700
Data Index: 3968502 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7264. Min Act: -0.1700
Data Index: 5460919 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6951. Min Act: -0.1700
Data Index: 4279942 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.7264. Min Act: -0.1700
Data Index: 234673 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6951. Min Act: -0.1700
Data Index: 3636335 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6951. Min Act: -0.1700
Data Index: 6001603 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1014. Min Range: -6.1014
Max Act: 5.6951. Min Act: -0.1700
Data Index: 6210516 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19