Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3830 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0942. Min Act: -0.0001
Data Index: 766943 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0792. Min Act: -0.0001
Data Index: 1106116 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0695. Min Act: -0.0001
Data Index: 1119018 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0728. Min Act: -0.0001
Data Index: 1129594 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0692. Min Act: -0.0001
Data Index: 390031 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0717. Min Act: -0.0001
Data Index: 906551 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0730. Min Act: -0.0001
Data Index: 201120 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0645. Min Act: -0.0001
Data Index: 383390 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0661. Min Act: -0.0001
Data Index: 1155235 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0588. Min Act: -0.0001
Data Index: 629029 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0658. Min Act: -0.0001
Data Index: 885095 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0628. Min Act: -0.0001
Data Index: 241092 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0610. Min Act: -0.0001
Data Index: 278599 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0580. Min Act: -0.0001
Data Index: 221327 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0578. Min Act: -0.0001
Data Index: 708460 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0606. Min Act: -0.0001
Data Index: 1256174 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0588. Min Act: -0.0001
Data Index: 577939 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0589. Min Act: -0.0001
Data Index: 515370 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0558. Min Act: -0.0001
Data Index: 1264693 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0942. Min Range: -0.0942
Max Act: 0.0519. Min Act: -0.0001
Data Index: 680924 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19