Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1428 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0003

Data Index: 597346 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1085561 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0299. Min Act: -0.0003

Data Index: 123059 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0310. Min Act: -0.0004

Data Index: 373308 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0307. Min Act: -0.0003

Data Index: 601949 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0270. Min Act: -0.0003

Data Index: 772031 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1282395 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0282. Min Act: -0.0003

Data Index: 860399 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0308. Min Act: -0.0003

Data Index: 216377 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0287. Min Act: -0.0003

Data Index: 953955 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1193619 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1158038 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1257584 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1185895 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0300. Min Act: -0.0003

Data Index: 822904 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0291. Min Act: -0.0004

Data Index: 1254907 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0270. Min Act: -0.0003

Data Index: 132193 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0286. Min Act: -0.0003

Data Index: 495145 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1109155 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0275. Min Act: -0.0003

Data Index: 983209 (C4 (Web Text))

Max Activating Token Index: 633