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

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

Neuron 5884 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0466. Min Range: -1.0466

Max Act: 1.0466. Min Act: -0.0001

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.9563. Min Act: -0.0001

Data Index: 1346002 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.9635. Min Act: -0.0001

Data Index: 221558 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.9360. Min Act: -0.0001

Data Index: 806186 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.9224. Min Act: -0.0001

Data Index: 891489 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 1.0466. Min Range: -1.0466

Max Act: 1.0067. Min Act: -0.0001

Data Index: 539677 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7723. Min Act: -0.0001

Data Index: 372251 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7815. Min Act: -0.0001

Data Index: 1009052 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7834. Min Act: -0.0001

Data Index: 870659 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6577. Min Act: -0.0001

Data Index: 643733 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8596. Min Act: -0.0001

Data Index: 1086546 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7177. Min Act: -0.0001

Data Index: 1225462 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7469. Min Act: -0.0001

Data Index: 1108910 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.5358. Min Act: -0.0001

Data Index: 814450 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7317. Min Act: -0.0001

Data Index: 175987 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1185109 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6873. Min Act: -0.0001

Data Index: 470868 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7391. Min Act: -0.0001

Data Index: 733449 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1054311 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7064. Min Act: -0.0001

Data Index: 231393 (C4 (Web Text))

Max Activating Token Index: 759