Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3003 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.3495. Min Range: -2.3495
Max Act: 2.3495. Min Act: -0.0001
Data Index: 892449 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3495. Min Range: -2.3495
Max Act: 2.1732. Min Act: -0.0001
Data Index: 403369 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3495. Min Range: -2.3495
Max Act: 2.0481. Min Act: -0.0001
Data Index: 173226 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3495. Min Range: -2.3495
Max Act: 2.1504. Min Act: -0.0001
Data Index: 1091987 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3495. Min Range: -2.3495
Max Act: 2.2421. Min Act: -0.0001
Data Index: 1036755 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3495. Min Range: -2.3495
Max Act: 2.1062. Min Act: -0.0001
Data Index: 857223 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3495. Min Range: -2.3495
Max Act: 2.1835. Min Act: -0.0001
Data Index: 452643 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.9986. Min Act: -0.0001
Data Index: 598516 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.9443. Min Act: -0.0001
Data Index: 91312 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.8086. Min Act: -0.0001
Data Index: 1070017 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3495. Min Range: -2.3495
Max Act: 2.0126. Min Act: -0.0001
Data Index: 72900 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.7681. Min Act: -0.0001
Data Index: 854970 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.8357. Min Act: -0.0001
Data Index: 399995 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.8415. Min Act: -0.0001
Data Index: 765816 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.8304. Min Act: -0.0001
Data Index: 603665 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.9878. Min Act: -0.0001
Data Index: 1300252 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3495. Min Range: -2.3495
Max Act: 2.0955. Min Act: -0.0001
Data Index: 521991 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.6594. Min Act: -0.0001
Data Index: 453540 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.9306. Min Act: -0.0001
Data Index: 102908 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3495. Min Range: -2.3495
Max Act: 1.7701. Min Act: -0.0001
Data Index: 780575 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19