Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3777 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2517. Min Range: -1.2517
Max Act: 1.2517. Min Act: -0.0001
Data Index: 1226542 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2517. Min Range: -1.2517
Max Act: 1.1693. Min Act: -0.0001
Data Index: 837329 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2517. Min Range: -1.2517
Max Act: 1.0849. Min Act: -0.0001
Data Index: 807639 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2517. Min Range: -1.2517
Max Act: 1.0628. Min Act: -0.0001
Data Index: 1226469 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.9242. Min Act: -0.0001
Data Index: 323821 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8890. Min Act: -0.0001
Data Index: 1309823 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8035. Min Act: -0.0001
Data Index: 671631 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8705. Min Act: -0.0001
Data Index: 75544 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8603. Min Act: -0.0001
Data Index: 410170 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8229. Min Act: -0.0001
Data Index: 594762 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8200. Min Act: -0.0001
Data Index: 1258262 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8610. Min Act: -0.0001
Data Index: 581636 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8452. Min Act: -0.0001
Data Index: 497057 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8115. Min Act: -0.0001
Data Index: 1075753 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8293. Min Act: -0.0001
Data Index: 635602 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.7316. Min Act: -0.0001
Data Index: 748100 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.7997. Min Act: -0.0001
Data Index: 781894 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.8017. Min Act: -0.0001
Data Index: 814113 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.7592. Min Act: -0.0001
Data Index: 571931 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2517. Min Range: -1.2517
Max Act: 0.7127. Min Act: -0.0001
Data Index: 21540 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19