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

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

Neuron 6030 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.6602. Min Act: -0.0002

Data Index: 662504 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.6332. Min Act: -0.0002

Data Index: 553517 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.6022. Min Act: -0.0002

Data Index: 1238138 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.6190. Min Act: -0.0002

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5977. Min Act: -0.0002

Data Index: 333276 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5973. Min Act: -0.0002

Data Index: 1348371 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.6134. Min Act: -0.0001

Data Index: 725436 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5925. Min Act: -0.0002

Data Index: 212551 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5495. Min Act: -0.0002

Data Index: 353958 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5610. Min Act: -0.0002

Data Index: 1106935 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5583. Min Act: -0.0002

Data Index: 18578 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5548. Min Act: -0.0002

Data Index: 617795 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5537. Min Act: -0.0002

Data Index: 1227300 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5500. Min Act: -0.0002

Data Index: 940426 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5426. Min Act: -0.0002

Data Index: 40610 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5271. Min Act: -0.0002

Data Index: 518668 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5091. Min Act: -0.0001

Data Index: 747437 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5405. Min Act: -0.0002

Data Index: 818340 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5226. Min Act: -0.0002

Data Index: 318796 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5182. Min Act: -0.0002

Data Index: 1096861 (C4 (Web Text))

Max Activating Token Index: 635