Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 260 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0888. Min Act: -0.0004
Data Index: 748967 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0889. Min Act: -0.0004
Data Index: 1291906 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0845. Min Act: -0.0004
Data Index: 1113351 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0814. Min Act: -0.0004
Data Index: 813770 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0741. Min Act: -0.0004
Data Index: 571033 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0828. Min Act: -0.0004
Data Index: 897927 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0789. Min Act: -0.0004
Data Index: 769409 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0781. Min Act: -0.0004
Data Index: 150764 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0742. Min Act: -0.0004
Data Index: 57434 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0768. Min Act: -0.0004
Data Index: 1096910 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0696. Min Act: -0.0004
Data Index: 968932 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0690. Min Act: -0.0004
Data Index: 603403 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0779. Min Act: -0.0004
Data Index: 742613 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0750. Min Act: -0.0004
Data Index: 1113499 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0712. Min Act: -0.0004
Data Index: 1099954 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0740. Min Act: -0.0004
Data Index: 1393485 (Python Code)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0739. Min Act: -0.0004
Data Index: 1016033 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0704. Min Act: -0.0004
Data Index: 1304968 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0736. Min Act: -0.0004
Data Index: 326158 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0889. Min Range: -0.0889
Max Act: 0.0728. Min Act: -0.0004
Data Index: 1449029 (Python Code)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19