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

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

Neuron 392 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.5195. Min Act: -0.0000

Data Index: 634188 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1015478 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.4095. Min Act: -0.0000

Data Index: 890281 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.4060. Min Act: -0.0000

Data Index: 934951 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1276625 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3739. Min Act: -0.0000

Data Index: 731496 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3898. Min Act: -0.0000

Data Index: 624015 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3778. Min Act: -0.0000

Data Index: 442787 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3683. Min Act: -0.0000

Data Index: 17783 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3685. Min Act: -0.0000

Data Index: 819846 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3649. Min Act: -0.0000

Data Index: 607290 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1045383 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3380. Min Act: -0.0000

Data Index: 521095 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3247. Min Act: -0.0000

Data Index: 139340 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1233247 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3182. Min Act: -0.0000

Data Index: 215556 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3254. Min Act: -0.0000

Data Index: 559525 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3262. Min Act: -0.0000

Data Index: 206563 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3303. Min Act: -0.0000

Data Index: 479456 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.5195. Min Range: -0.5195

Max Act: 0.3170. Min Act: -0.0000

Data Index: 505372 (C4 (Web Text))

Max Activating Token Index: 301