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

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

Neuron 395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.5240. Min Act: -0.0000

Data Index: 34759 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.5270. Min Act: -0.0000

Data Index: 566164 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.3213. Min Act: -0.0000

Data Index: 767492 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.2294. Min Act: -0.0000

Data Index: 144601 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.2215. Min Act: -0.0000

Data Index: 915647 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.1632. Min Act: -0.0000

Data Index: 604480 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1095453 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.1695. Min Act: -0.0000

Data Index: 373256 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1185523 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.1262. Min Act: -0.0000

Data Index: 1137479 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.1478. Min Act: -0.0000

Data Index: 925000 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1164104 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0933. Min Act: -0.0000

Data Index: 577490 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0558. Min Act: -0.0000

Data Index: 417682 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0920. Min Act: -0.0000

Data Index: 704187 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0871. Min Act: -0.0000

Data Index: 507451 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0468. Min Act: -0.0000

Data Index: 590942 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0802. Min Act: -0.0000

Data Index: 293041 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0775. Min Act: -0.0000

Data Index: 434979 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0470. Min Act: -0.0000

Data Index: 518309 (C4 (Web Text))

Max Activating Token Index: 300