Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 783 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0003

Data Index: 620143 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0401. Min Act: -0.0003

Data Index: 603907 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1317275 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0361. Min Act: -0.0003

Data Index: 990530 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0311. Min Act: -0.0003

Data Index: 615162 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0292. Min Act: -0.0003

Data Index: 282945 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0284. Min Act: -0.0003

Data Index: 103340 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0283. Min Act: -0.0003

Data Index: 582673 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0282. Min Act: -0.0003

Data Index: 800070 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0285. Min Act: -0.0003

Data Index: 222764 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0267. Min Act: -0.0003

Data Index: 183828 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0261. Min Act: -0.0003

Data Index: 615229 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0259. Min Act: -0.0003

Data Index: 236299 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0255. Min Act: -0.0003

Data Index: 644729 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0252. Min Act: -0.0004

Data Index: 1350491 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0244. Min Act: -0.0003

Data Index: 859383 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0243. Min Act: -0.0003

Data Index: 618850 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0241. Min Act: -0.0003

Data Index: 850493 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0237. Min Act: -0.0004

Data Index: 30235 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1040533 (C4 (Web Text))

Max Activating Token Index: 98