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

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

Neuron 4734 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: 0.0321. Min Range: -0.0321

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1102640 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1170584 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0276. Min Act: -0.0003

Data Index: 432500 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1096109 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0264. Min Act: -0.0003

Data Index: 317994 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0268. Min Act: -0.0003

Data Index: 859302 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0263. Min Act: -0.0003

Data Index: 142034 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0262. Min Act: -0.0003

Data Index: 992788 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0253. Min Act: -0.0003

Data Index: 572957 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0255. Min Act: -0.0003

Data Index: 551929 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0256. Min Act: -0.0003

Data Index: 773081 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0251. Min Act: -0.0003

Data Index: 443952 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0247. Min Act: -0.0003

Data Index: 559926 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0260. Min Act: -0.0003

Data Index: 31025 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1101628 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0260. Min Act: -0.0003

Data Index: 278612 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0250. Min Act: -0.0003

Data Index: 135348 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0249. Min Act: -0.0003

Data Index: 853585 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1082023 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0252. Min Act: -0.0003

Data Index: 419341 (C4 (Web Text))

Max Activating Token Index: 667