Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1874 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.7773. Min Act: -0.0001
Data Index: 350507 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.8112. Min Act: -0.0001
Data Index: 1440590 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.7328. Min Act: -0.0001
Data Index: 144986 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6607. Min Act: -0.0001
Data Index: 366491 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6805. Min Act: -0.0001
Data Index: 635448 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6183. Min Act: -0.0001
Data Index: 1518683 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6335. Min Act: -0.0001
Data Index: 572178 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6571. Min Act: -0.0001
Data Index: 786631 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6289. Min Act: -0.0001
Data Index: 27914 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6417. Min Act: -0.0001
Data Index: 1177773 (The Pile)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6759. Min Act: -0.0001
Data Index: 1633117 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.5541. Min Act: -0.0001
Data Index: 1427030 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6456. Min Act: -0.0001
Data Index: 1631329 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6962. Min Act: -0.0001
Data Index: 1462861 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6262. Min Act: -0.0001
Data Index: 478323 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6296. Min Act: -0.0001
Data Index: 890406 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.4527. Min Act: -0.0001
Data Index: 204031 (The Pile)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6037. Min Act: -0.0001
Data Index: 1748453 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6900. Min Act: -0.0001
Data Index: 644716 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8112. Min Range: -0.8112
Max Act: 0.6217. Min Act: -0.0001
Data Index: 1210714 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19