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

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

Neuron 4626 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: 0.1473. Min Range: -0.1473

Max Act: 0.1438. Min Act: -0.0000

Data Index: 507201 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1473. Min Act: -0.0000

Data Index: 432058 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1244. Min Act: -0.0000

Data Index: 196667 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0978. Min Act: -0.0000

Data Index: 467408 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0889. Min Act: -0.0000

Data Index: 530493 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1239873 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1098740 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1295351 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0623. Min Act: -0.0000

Data Index: 1293467 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0529. Min Act: -0.0000

Data Index: 91161 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0745. Min Act: -0.0000

Data Index: 24183 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0679. Min Act: -0.0000

Data Index: 641697 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1319376 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1091670 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1430692 (Python Code)

Max Activating Token Index: 316

Text #15

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1341872 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0540. Min Act: -0.0000

Data Index: 432655 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0408. Min Act: -0.0000

Data Index: 611915 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0615. Min Act: -0.0000

Data Index: 273601 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1094282 (C4 (Web Text))

Max Activating Token Index: 188