Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 578 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1205856 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1172158 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1532502 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0274. Min Act: -0.0003

Data Index: 545518 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0274. Min Act: -0.0004

Data Index: 936165 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1224683 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0267. Min Act: -0.0003

Data Index: 13201 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0263. Min Act: -0.0003

Data Index: 301186 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0261. Min Act: -0.0004

Data Index: 598633 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1374810 (Python Code)

Max Activating Token Index: 956

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1230405 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0246. Min Act: -0.0003

Data Index: 808943 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0240. Min Act: -0.0003

Data Index: 147307 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1309870 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1337917 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0249. Min Act: -0.0003

Data Index: 110566 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1038911 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1013562 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0237. Min Act: -0.0003

Data Index: 888908 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0241. Min Act: -0.0003

Data Index: 679471 (C4 (Web Text))

Max Activating Token Index: 242