Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1415 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0978. Min Act: -0.0002

Data Index: 766698 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0909. Min Act: -0.0002

Data Index: 968654 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0755. Min Act: -0.0002

Data Index: 648125 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1233179 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0738. Min Act: -0.0002

Data Index: 375600 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0676. Min Act: -0.0003

Data Index: 567163 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0694. Min Act: -0.0003

Data Index: 377910 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0669. Min Act: -0.0002

Data Index: 355610 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0641. Min Act: -0.0003

Data Index: 937555 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0655. Min Act: -0.0002

Data Index: 132557 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1322918 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0608. Min Act: -0.0002

Data Index: 734239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1137447 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0579. Min Act: -0.0003

Data Index: 748208 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1087995 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0547. Min Act: -0.0003

Data Index: 558785 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0494. Min Act: -0.0003

Data Index: 837927 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0516. Min Act: -0.0003

Data Index: 707195 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0480. Min Act: -0.0002

Data Index: 397412 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0478. Min Act: -0.0003

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 59