Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1391 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0265. Min Act: -0.0003

Data Index: 333936 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0269. Min Act: -0.0003

Data Index: 990793 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0252. Min Act: -0.0003

Data Index: 231405 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0243. Min Act: -0.0003

Data Index: 492141 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1298955 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0242. Min Act: -0.0003

Data Index: 349224 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0245. Min Act: -0.0003

Data Index: 431985 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1258124 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1639181 (Python Code)

Max Activating Token Index: 430

Text #9

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0227. Min Act: -0.0003

Data Index: 144830 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0222. Min Act: -0.0003

Data Index: 285958 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1350665 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0222. Min Act: -0.0003

Data Index: 469020 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0219. Min Act: -0.0003

Data Index: 923449 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1356610 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0205. Min Act: -0.0003

Data Index: 151753 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1166350 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0197. Min Act: -0.0003

Data Index: 804078 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0209. Min Act: -0.0003

Data Index: 95197 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0217. Min Act: -0.0003

Data Index: 194780 (C4 (Web Text))

Max Activating Token Index: 967