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

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

Neuron 258 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: 0.0463. Min Range: -0.0463

Max Act: 0.0463. Min Act: -0.0003

Data Index: 293971 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0453. Min Act: -0.0003

Data Index: 571562 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0431. Min Act: -0.0003

Data Index: 482627 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0430. Min Act: -0.0004

Data Index: 1139112 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0431. Min Act: -0.0004

Data Index: 692466 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0421. Min Act: -0.0003

Data Index: 959850 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0428. Min Act: -0.0003

Data Index: 90703 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1078701 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0406. Min Act: -0.0003

Data Index: 206806 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1227554 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1251869 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0398. Min Act: -0.0003

Data Index: 497424 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1154407 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0397. Min Act: -0.0003

Data Index: 28325 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1188 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0384. Min Act: -0.0004

Data Index: 568888 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0375. Min Act: -0.0003

Data Index: 42053 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0396. Min Act: -0.0003

Data Index: 297153 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0388. Min Act: -0.0003

Data Index: 251510 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0381. Min Act: -0.0003

Data Index: 575636 (C4 (Web Text))

Max Activating Token Index: 693