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

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

Neuron 2205 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0004

Data Index: 804112 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0316. Min Act: -0.0004

Data Index: 206420 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1217406 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0299. Min Act: -0.0004

Data Index: 617030 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0271. Min Act: -0.0004

Data Index: 566417 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0259. Min Act: -0.0004

Data Index: 313282 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0267. Min Act: -0.0004

Data Index: 340159 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0256. Min Act: -0.0004

Data Index: 115427 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0234. Min Act: -0.0004

Data Index: 487619 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0248. Min Act: -0.0004

Data Index: 874431 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0242. Min Act: -0.0004

Data Index: 383938 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0242. Min Act: -0.0004

Data Index: 1229865 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0236. Min Act: -0.0004

Data Index: 170716 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0241. Min Act: -0.0004

Data Index: 904230 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0239. Min Act: -0.0004

Data Index: 1088498 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0226. Min Act: -0.0004

Data Index: 1077263 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0232. Min Act: -0.0004

Data Index: 123084 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0226. Min Act: -0.0004

Data Index: 205929 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0231. Min Act: -0.0004

Data Index: 753122 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0226. Min Act: -0.0004

Data Index: 448529 (C4 (Web Text))

Max Activating Token Index: 927