Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 3 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1252925 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0248. Min Act: -0.0006

Data Index: 288124 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0234. Min Act: -0.0006

Data Index: 726694 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1111874 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0222. Min Act: -0.0006

Data Index: 407499 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1002911 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1069347 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0217. Min Act: -0.0006

Data Index: 19683 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0218. Min Act: -0.0006

Data Index: 82586 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0222. Min Act: -0.0006

Data Index: 924716 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0210. Min Act: -0.0006

Data Index: 50841 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0225. Min Act: -0.0006

Data Index: 771035 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0213. Min Act: -0.0006

Data Index: 914375 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0218. Min Act: -0.0006

Data Index: 570875 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0218. Min Act: -0.0006

Data Index: 501360 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1160682 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0212. Min Act: -0.0006

Data Index: 426697 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0211. Min Act: -0.0006

Data Index: 945844 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1228947 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0206. Min Act: -0.0006

Data Index: 371995 (C4 (Web Text))

Max Activating Token Index: 397