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

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

Neuron 1546 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: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0003

Data Index: 479633 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0249. Min Act: -0.0003

Data Index: 869657 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0212. Min Act: -0.0003

Data Index: 961732 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0219. Min Act: -0.0002

Data Index: 258148 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0235. Min Act: -0.0002

Data Index: 933032 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1203599 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0225. Min Act: -0.0003

Data Index: 465976 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0214. Min Act: -0.0003

Data Index: 242901 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1423666 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1415665 (Python Code)

Max Activating Token Index: 246

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0203. Min Act: -0.0003

Data Index: 647874 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1536701 (Python Code)

Max Activating Token Index: 595

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0218. Min Act: -0.0003

Data Index: 794316 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1014831 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1281464 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0212. Min Act: -0.0003

Data Index: 336649 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0219. Min Act: -0.0003

Data Index: 406072 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0222. Min Act: -0.0003

Data Index: 431821 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0204. Min Act: -0.0003

Data Index: 155866 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1552690 (Python Code)

Max Activating Token Index: 47