Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3785 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0933. Min Act: -0.0002
Data Index: 375600 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0961. Min Act: -0.0001
Data Index: 464067 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0866. Min Act: -0.0001
Data Index: 1403165 (Python Code)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0954. Min Act: -0.0001
Data Index: 1133961 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0892. Min Act: -0.0001
Data Index: 1358923 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0828. Min Act: -0.0001
Data Index: 1244440 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0790. Min Act: -0.0001
Data Index: 12988 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0813. Min Act: -0.0001
Data Index: 504552 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0736. Min Act: -0.0001
Data Index: 894531 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0768. Min Act: -0.0001
Data Index: 1283480 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0714. Min Act: -0.0001
Data Index: 575043 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0693. Min Act: -0.0001
Data Index: 668843 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0735. Min Act: -0.0001
Data Index: 680057 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0780. Min Act: -0.0001
Data Index: 392195 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0801. Min Act: -0.0001
Data Index: 1426018 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0747. Min Act: -0.0001
Data Index: 1228132 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0775. Min Act: -0.0001
Data Index: 1141284 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0794. Min Act: -0.0001
Data Index: 1157408 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0690. Min Act: -0.0001
Data Index: 960463 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0961. Min Range: -0.0961
Max Act: 0.0840. Min Act: -0.0001
Data Index: 1021578 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19