Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 46 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0948. Min Act: -0.0003

Data Index: 574745 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0926. Min Act: -0.0003

Data Index: 1304286 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0895. Min Act: -0.0003

Data Index: 385408 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0825. Min Act: -0.0003

Data Index: 973432 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1234569 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0751. Min Act: -0.0003

Data Index: 374878 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0770. Min Act: -0.0003

Data Index: 1255027 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0741. Min Act: -0.0003

Data Index: 353935 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0757. Min Act: -0.0003

Data Index: 43254 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0728. Min Act: -0.0003

Data Index: 286127 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0710. Min Act: -0.0003

Data Index: 238503 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0701. Min Act: -0.0003

Data Index: 750779 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0661. Min Act: -0.0003

Data Index: 850354 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0641. Min Act: -0.0003

Data Index: 596762 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0693. Min Act: -0.0003

Data Index: 682155 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0635. Min Act: -0.0003

Data Index: 900967 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0670. Min Act: -0.0003

Data Index: 680901 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0604. Min Act: -0.0003

Data Index: 274344 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0621. Min Act: -0.0004

Data Index: 1150168 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0563. Min Act: -0.0003

Data Index: 578718 (C4 (Web Text))

Max Activating Token Index: 796