Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6112 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.5391. Min Act: -0.0001
Data Index: 1305411 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.5521. Min Act: -0.0001
Data Index: 666007 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.8962. Min Act: -0.0001
Data Index: 1178795 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.3187. Min Act: -0.0001
Data Index: 1206890 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.3966. Min Act: -0.0001
Data Index: 194199 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.3741. Min Act: -0.0001
Data Index: 1195621 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.4679. Min Act: -0.0001
Data Index: 1353409 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.4396. Min Act: -0.0001
Data Index: 796590 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.3841. Min Act: -0.0001
Data Index: 778185 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.3582. Min Act: -0.0001
Data Index: 376547 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.3466. Min Act: -0.0001
Data Index: 272183 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.2630. Min Act: -0.0001
Data Index: 724454 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.1684. Min Act: -0.0001
Data Index: 1052141 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.2251. Min Act: -0.0001
Data Index: 602663 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.1043. Min Act: -0.0001
Data Index: 275304 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.0324. Min Act: -0.0001
Data Index: 403838 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.1383. Min Act: -0.0001
Data Index: 1055747 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.1319. Min Act: -0.0001
Data Index: 872856 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.0717. Min Act: -0.0001
Data Index: 617733 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8962. Min Range: -2.8962
Max Act: 2.0670. Min Act: -0.0001
Data Index: 388189 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19