Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 571 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1124369 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0428. Min Act: -0.0001

Data Index: 975531 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1570077 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1067750 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1475691 (Python Code)

Max Activating Token Index: 307

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0372. Min Act: -0.0001

Data Index: 996142 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0451. Min Act: -0.0001

Data Index: 752640 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0421. Min Act: -0.0002

Data Index: 267332 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1471187 (Python Code)

Max Activating Token Index: 625

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0504. Min Act: -0.0001

Data Index: 770290 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0386. Min Act: -0.0001

Data Index: 221576 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0541. Min Act: -0.0002

Data Index: 694047 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0378. Min Act: -0.0002

Data Index: 812903 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0425. Min Act: -0.0001

Data Index: 608327 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0377. Min Act: -0.0001

Data Index: 855066 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1507783 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1543099 (Python Code)

Max Activating Token Index: 392

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0325. Min Act: -0.0001

Data Index: 173555 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0413. Min Act: -0.0002

Data Index: 331979 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0421. Min Act: -0.0002

Data Index: 812524 (C4 (Web Text))

Max Activating Token Index: 541