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

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

Neuron 199 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: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0002

Data Index: 777258 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0619. Min Act: -0.0002

Data Index: 259376 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0562. Min Act: -0.0002

Data Index: 567295 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1215328 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0542. Min Act: -0.0002

Data Index: 101796 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1300941 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0479. Min Act: -0.0002

Data Index: 592167 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0469. Min Act: -0.0002

Data Index: 650395 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0454. Min Act: -0.0002

Data Index: 133546 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0468. Min Act: -0.0002

Data Index: 185328 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1119921 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1218516 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0455. Min Act: -0.0002

Data Index: 710166 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0450. Min Act: -0.0002

Data Index: 187119 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0450. Min Act: -0.0002

Data Index: 433878 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0480. Min Act: -0.0002

Data Index: 918861 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0417. Min Act: -0.0002

Data Index: 725264 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0439. Min Act: -0.0002

Data Index: 763213 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1295393 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0438. Min Act: -0.0002

Data Index: 782438 (C4 (Web Text))

Max Activating Token Index: 882