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

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

Neuron 435 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1583436 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1150216 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0216. Min Act: -0.0003

Data Index: 624934 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1352522 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1111548 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0213. Min Act: -0.0003

Data Index: 698194 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0215. Min Act: -0.0004

Data Index: 434882 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0212. Min Act: -0.0003

Data Index: 965179 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0205. Min Act: -0.0003

Data Index: 769662 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1049881 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0195. Min Act: -0.0004

Data Index: 109209 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0201. Min Act: -0.0003

Data Index: 630048 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1112975 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0204. Min Act: -0.0003

Data Index: 18933 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0204. Min Act: -0.0003

Data Index: 250014 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1331219 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1258276 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0195. Min Act: -0.0003

Data Index: 639675 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0199. Min Act: -0.0003

Data Index: 939202 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1036182 (C4 (Web Text))

Max Activating Token Index: 3