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

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

Neuron 3559 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1271224 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0317. Min Act: -0.0003

Data Index: 737538 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1061501 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0314. Min Act: -0.0003

Data Index: 728253 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0314. Min Act: -0.0003

Data Index: 622904 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0303. Min Act: -0.0003

Data Index: 141901 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0289. Min Act: -0.0003

Data Index: 731824 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0282. Min Act: -0.0003

Data Index: 828562 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1333873 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1238273 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0287. Min Act: -0.0003

Data Index: 405244 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0281. Min Act: -0.0003

Data Index: 127135 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1089575 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0282. Min Act: -0.0003

Data Index: 889101 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0269. Min Act: -0.0003

Data Index: 574373 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1479229 (Python Code)

Max Activating Token Index: 46

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0267. Min Act: -0.0003

Data Index: 392145 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1121260 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0261. Min Act: -0.0003

Data Index: 774586 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0264. Min Act: -0.0003

Data Index: 107659 (C4 (Web Text))

Max Activating Token Index: 519