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

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

Neuron 4732 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0003

Data Index: 117990 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1018629 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0291. Min Act: -0.0002

Data Index: 987581 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1039102 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1187776 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0281. Min Act: -0.0002

Data Index: 153897 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0242. Min Act: -0.0002

Data Index: 929031 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0267. Min Act: -0.0002

Data Index: 315008 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0269. Min Act: -0.0002

Data Index: 731826 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0314. Min Act: -0.0002

Data Index: 483279 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0260. Min Act: -0.0002

Data Index: 526747 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0254. Min Act: -0.0003

Data Index: 52969 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0246. Min Act: -0.0002

Data Index: 175756 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0246. Min Act: -0.0002

Data Index: 859695 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0207. Min Act: -0.0002

Data Index: 146350 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1288972 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0196. Min Act: -0.0002

Data Index: 276359 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0243. Min Act: -0.0002

Data Index: 601661 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0239. Min Act: -0.0002

Data Index: 647670 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0240. Min Act: -0.0002

Data Index: 790658 (C4 (Web Text))

Max Activating Token Index: 852