Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3297 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1726. Min Act: -0.0003

Data Index: 753251 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1697. Min Act: -0.0003

Data Index: 767964 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1677. Min Act: -0.0003

Data Index: 1315660 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1596. Min Act: -0.0003

Data Index: 583123 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1538. Min Act: -0.0003

Data Index: 1286678 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1579. Min Act: -0.0003

Data Index: 916915 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1474. Min Act: -0.0002

Data Index: 1139508 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1469. Min Act: -0.0002

Data Index: 536923 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1392. Min Act: -0.0003

Data Index: 664105 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1437. Min Act: -0.0003

Data Index: 1129392 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1368. Min Act: -0.0003

Data Index: 1344478 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1428. Min Act: -0.0003

Data Index: 514014 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1354. Min Act: -0.0003

Data Index: 85406 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1299. Min Act: -0.0003

Data Index: 689963 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1327. Min Act: -0.0003

Data Index: 1005013 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1377. Min Act: -0.0003

Data Index: 12802 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1372. Min Act: -0.0003

Data Index: 162252 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1370. Min Act: -0.0003

Data Index: 631739 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1306. Min Act: -0.0003

Data Index: 1169556 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1349. Min Act: -0.0003

Data Index: 22627 (C4 (Web Text))

Max Activating Token Index: 951