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

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

Neuron 5320 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1285530 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0001

Data Index: 578828 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0472. Min Act: -0.0001

Data Index: 968964 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0458. Min Act: -0.0001

Data Index: 841835 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0401. Min Act: -0.0002

Data Index: 888936 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0397. Min Act: -0.0001

Data Index: 417544 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0434. Min Act: -0.0001

Data Index: 714935 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1316144 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0445. Min Act: -0.0001

Data Index: 468476 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0393. Min Act: -0.0002

Data Index: 819672 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0441. Min Act: -0.0001

Data Index: 534993 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0385. Min Act: -0.0001

Data Index: 626409 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1352342 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1282118 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0411. Min Act: -0.0001

Data Index: 441350 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1073077 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0382. Min Act: -0.0001

Data Index: 949896 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1288117 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1598279 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1000421 (C4 (Web Text))

Max Activating Token Index: 645