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

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

Neuron 1460 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.5627. Min Act: -0.0000

Data Index: 968689 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1304492 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1032351 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4791. Min Act: -0.0000

Data Index: 17773 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4810. Min Act: -0.0000

Data Index: 933884 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1159335 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4781. Min Act: -0.0000

Data Index: 230114 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4569. Min Act: -0.0000

Data Index: 535882 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4421. Min Act: -0.0000

Data Index: 411091 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4286. Min Act: -0.0000

Data Index: 660223 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4215. Min Act: -0.0000

Data Index: 895563 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4303. Min Act: -0.0000

Data Index: 335622 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1125358 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4367. Min Act: -0.0000

Data Index: 5765 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4227. Min Act: -0.0000

Data Index: 410840 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4380. Min Act: -0.0001

Data Index: 1197523 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4228. Min Act: -0.0000

Data Index: 763277 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4200. Min Act: -0.0000

Data Index: 975476 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4360. Min Act: -0.0000

Data Index: 406427 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4317. Min Act: -0.0000

Data Index: 114899 (C4 (Web Text))

Max Activating Token Index: 724