Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1584. Min Act: -0.0003

Data Index: 760236 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1657. Min Act: -0.0003

Data Index: 544625 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1595. Min Act: -0.0004

Data Index: 306523 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1561. Min Act: -0.0002

Data Index: 852742 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1482. Min Act: -0.0002

Data Index: 697592 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1421. Min Act: -0.0003

Data Index: 328345 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1389. Min Act: -0.0002

Data Index: 1320444 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1396. Min Act: -0.0003

Data Index: 127607 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1393. Min Act: -0.0002

Data Index: 1046903 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1391. Min Act: -0.0003

Data Index: 151714 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1382. Min Act: -0.0003

Data Index: 594453 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1375. Min Act: -0.0003

Data Index: 47225 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1377. Min Act: -0.0003

Data Index: 77917 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1324. Min Act: -0.0002

Data Index: 572944 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1376. Min Act: -0.0003

Data Index: 1107481 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1412. Min Act: -0.0003

Data Index: 1291727 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1349. Min Act: -0.0002

Data Index: 685108 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1375. Min Act: -0.0002

Data Index: 393860 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1394. Min Act: -0.0003

Data Index: 299748 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.1657. Min Range: -0.1657

Max Act: 0.1400. Min Act: -0.0002

Data Index: 530329 (C4 (Web Text))

Max Activating Token Index: 369