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

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

Neuron 1668 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: 686287 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0273. Min Act: -0.0004

Data Index: 1467393 (Python Code)

Max Activating Token Index: 842

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0294. Min Act: -0.0004

Data Index: 1464477 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0310. Min Act: -0.0004

Data Index: 210785 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0241. Min Act: -0.0004

Data Index: 1051291 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0247. Min Act: -0.0004

Data Index: 737895 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1464276 (Python Code)

Max Activating Token Index: 526

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1568967 (Python Code)

Max Activating Token Index: 94

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0223. Min Act: -0.0004

Data Index: 989932 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0206. Min Act: -0.0004

Data Index: 999591 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0229. Min Act: -0.0004

Data Index: 957858 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0248. Min Act: -0.0004

Data Index: 918744 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0209. Min Act: -0.0004

Data Index: 1484248 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0184. Min Act: -0.0004

Data Index: 778435 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0197. Min Act: -0.0004

Data Index: 1049615 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1622583 (Python Code)

Max Activating Token Index: 364

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0194. Min Act: -0.0004

Data Index: 552750 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0186. Min Act: -0.0004

Data Index: 1274364 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0196. Min Act: -0.0004

Data Index: 803010 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0199. Min Act: -0.0004

Data Index: 1374934 (Python Code)

Max Activating Token Index: 331