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

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

Neuron 742 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1652. Min Range: -2.1652

Max Act: 2.1652. Min Act: -0.0000

Data Index: 200311 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.7250. Min Act: -0.0000

Data Index: 235860 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.7380. Min Act: -0.0000

Data Index: 330095 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.7961. Min Act: -0.0000

Data Index: 648275 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.8483. Min Act: -0.0000

Data Index: 134389 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.6152. Min Act: -0.0000

Data Index: 554106 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.5967. Min Act: -0.0000

Data Index: 1089509 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1224678 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.4171. Min Act: -0.0000

Data Index: 703947 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.2892. Min Act: -0.0000

Data Index: 50406 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.5229. Min Act: -0.0000

Data Index: 1224093 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.5254. Min Act: -0.0000

Data Index: 835338 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.2660. Min Act: -0.0000

Data Index: 7947 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.3196. Min Act: -0.0000

Data Index: 1308667 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.4384. Min Act: -0.0000

Data Index: 191491 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.3327. Min Act: -0.0000

Data Index: 1243773 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.4479. Min Act: -0.0000

Data Index: 651110 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.3206. Min Act: -0.0000

Data Index: 585833 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.3194. Min Act: -0.0000

Data Index: 364734 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 2.1652. Min Range: -2.1652

Max Act: 1.2920. Min Act: -0.0000

Data Index: 183758 (C4 (Web Text))

Max Activating Token Index: 584