Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 610 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2016. Min Act: -0.0002

Data Index: 837735 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2257. Min Act: -0.0002

Data Index: 1128260 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1574. Min Act: -0.0002

Data Index: 639305 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1511. Min Act: -0.0002

Data Index: 235893 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1577. Min Act: -0.0002

Data Index: 332896 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1484. Min Act: -0.0002

Data Index: 727011 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1408. Min Act: -0.0002

Data Index: 999265 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1384. Min Act: -0.0002

Data Index: 1088472 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1438. Min Act: -0.0002

Data Index: 970402 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1416. Min Act: -0.0002

Data Index: 1267530 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1468. Min Act: -0.0002

Data Index: 358053 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1430. Min Act: -0.0002

Data Index: 431080 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1291. Min Act: -0.0002

Data Index: 2112 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1339323 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1358. Min Act: -0.0001

Data Index: 607944 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1208. Min Act: -0.0002

Data Index: 293699 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1327. Min Act: -0.0002

Data Index: 19403 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1328. Min Act: -0.0002

Data Index: 112716 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1513. Min Act: -0.0002

Data Index: 632530 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1249. Min Act: -0.0002

Data Index: 1300548 (C4 (Web Text))

Max Activating Token Index: 262