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

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

Neuron 185 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2534. Min Range: -2.2534

Max Act: 2.2534. Min Act: -0.0000

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 2.2534. Min Range: -2.2534

Max Act: 2.0489. Min Act: -0.0000

Data Index: 1053232 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.9754. Min Act: -0.0000

Data Index: 733449 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.9238. Min Act: -0.0000

Data Index: 1202055 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.5265. Min Act: -0.0000

Data Index: 389013 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.4031. Min Act: -0.0000

Data Index: 1280897 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.4863. Min Act: -0.0000

Data Index: 1137122 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1307397 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.1445. Min Act: -0.0000

Data Index: 890140 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.1163. Min Act: -0.0000

Data Index: 875558 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1551897 (Python Code)

Max Activating Token Index: 779

Text #11

Max Range: 2.2534. Min Range: -2.2534

Max Act: 0.9892. Min Act: -0.0000

Data Index: 383881 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 2.2534. Min Range: -2.2534

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1361760 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 2.2534. Min Range: -2.2534

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1579625 (Python Code)

Max Activating Token Index: 801

Text #14

Max Range: 2.2534. Min Range: -2.2534

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1469653 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 2.2534. Min Range: -2.2534

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1569338 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 2.2534. Min Range: -2.2534

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1017783 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 2.2534. Min Range: -2.2534

Max Act: 0.9189. Min Act: -0.0000

Data Index: 838557 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 2.2534. Min Range: -2.2534

Max Act: 0.8779. Min Act: -0.0000

Data Index: 349105 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 2.2534. Min Range: -2.2534

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1562242 (Python Code)

Max Activating Token Index: 160