Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 820 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0006

Data Index: 764602 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0310. Min Act: -0.0006

Data Index: 379865 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1324805 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0301. Min Act: -0.0006

Data Index: 364345 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0298. Min Act: -0.0005

Data Index: 530340 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0282. Min Act: -0.0006

Data Index: 784699 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1248418 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1115143 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0282. Min Act: -0.0006

Data Index: 836002 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0284. Min Act: -0.0005

Data Index: 540340 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1162976 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0274. Min Act: -0.0006

Data Index: 738018 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0259. Min Act: -0.0006

Data Index: 837001 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0275. Min Act: -0.0006

Data Index: 25202 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0275. Min Act: -0.0006

Data Index: 1306894 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0260. Min Act: -0.0006

Data Index: 779950 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0263. Min Act: -0.0006

Data Index: 386948 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0005

Data Index: 832952 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0006

Data Index: 551738 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1351931 (C4 (Web Text))

Max Activating Token Index: 855