Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4057 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0228. Min Act: -0.0003

Data Index: 757773 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0234. Min Act: -0.0002

Data Index: 6104 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0221. Min Act: -0.0003

Data Index: 614429 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1219977 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0217. Min Act: -0.0003

Data Index: 977666 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0215. Min Act: -0.0002

Data Index: 842368 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1324451 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0203. Min Act: -0.0002

Data Index: 186627 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0205. Min Act: -0.0003

Data Index: 529303 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0195. Min Act: -0.0003

Data Index: 541931 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0204. Min Act: -0.0003

Data Index: 370408 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0206. Min Act: -0.0003

Data Index: 44836 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1274063 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0197. Min Act: -0.0003

Data Index: 435955 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0195. Min Act: -0.0003

Data Index: 583812 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0191. Min Act: -0.0002

Data Index: 267221 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0202. Min Act: -0.0003

Data Index: 755886 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0193. Min Act: -0.0002

Data Index: 74145 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0193. Min Act: -0.0003

Data Index: 529657 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0193. Min Act: -0.0003

Data Index: 510766 (C4 (Web Text))

Max Activating Token Index: 1