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

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

Neuron 976 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4301. Min Act: -0.0003

Data Index: 1656738 (Python Code)

Max Activating Token Index: 472

Text #1

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4034. Min Act: -0.0003

Data Index: 1448348 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4214. Min Act: -0.0003

Data Index: 1632645 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3840. Min Act: -0.0003

Data Index: 1373759 (Python Code)

Max Activating Token Index: 571

Text #4

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3802. Min Act: -0.0003

Data Index: 1614270 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3728. Min Act: -0.0003

Data Index: 1425224 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3869. Min Act: -0.0003

Data Index: 1448469 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3856. Min Act: -0.0003

Data Index: 1451822 (Python Code)

Max Activating Token Index: 329

Text #8

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3730. Min Act: -0.0003

Data Index: 1652750 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3966. Min Act: -0.0003

Data Index: 1433134 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3830. Min Act: -0.0003

Data Index: 1569703 (Python Code)

Max Activating Token Index: 118

Text #11

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3798. Min Act: -0.0003

Data Index: 1647591 (Python Code)

Max Activating Token Index: 46

Text #12

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3683. Min Act: -0.0003

Data Index: 1532967 (Python Code)

Max Activating Token Index: 950

Text #13

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3612. Min Act: -0.0003

Data Index: 1498355 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3793. Min Act: -0.0003

Data Index: 1628199 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3645. Min Act: -0.0004

Data Index: 1409212 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3654. Min Act: -0.0003

Data Index: 1589793 (Python Code)

Max Activating Token Index: 160

Text #17

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3615. Min Act: -0.0003

Data Index: 1401648 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3591. Min Act: -0.0003

Data Index: 1424784 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3724. Min Act: -0.0003

Data Index: 1419179 (Python Code)

Max Activating Token Index: 627