Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 476 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1745. Min Act: -0.0000

Data Index: 955452 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1561. Min Act: -0.0000

Data Index: 66031 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.1426. Min Act: -0.0000

Data Index: 1037296 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0285. Min Act: -0.0000

Data Index: 730356 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0510. Min Act: -0.0000

Data Index: 307061 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0119. Min Act: -0.0000

Data Index: 413390 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0027. Min Act: -0.0000

Data Index: 339367 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0468. Min Act: -0.0000

Data Index: 372854 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9833. Min Act: -0.0000

Data Index: 182792 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1169938 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9406. Min Act: -0.0000

Data Index: 878651 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9130. Min Act: -0.0000

Data Index: 669457 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 1.1745. Min Range: -1.1745

Max Act: 1.0578. Min Act: -0.0000

Data Index: 214052 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8764. Min Act: -0.0000

Data Index: 485839 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1095835 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9722. Min Act: -0.0000

Data Index: 635830 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1072472 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1101713 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8720. Min Act: -0.0000

Data Index: 587384 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 1.1745. Min Range: -1.1745

Max Act: 0.8097. Min Act: -0.0000

Data Index: 454955 (C4 (Web Text))

Max Activating Token Index: 221