Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 15 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0270. Min Act: -0.0006

Data Index: 846162 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0275. Min Act: -0.0006

Data Index: 67713 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0251. Min Act: -0.0006

Data Index: 72711 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0256. Min Act: -0.0006

Data Index: 557194 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1161352 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1228267 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0261. Min Act: -0.0006

Data Index: 713696 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1353654 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0229. Min Act: -0.0006

Data Index: 2730 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0243. Min Act: -0.0006

Data Index: 298333 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0253. Min Act: -0.0006

Data Index: 525876 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0243. Min Act: -0.0006

Data Index: 190136 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0245. Min Act: -0.0006

Data Index: 506506 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0239. Min Act: -0.0006

Data Index: 244450 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0240. Min Act: -0.0006

Data Index: 496862 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0244. Min Act: -0.0006

Data Index: 540848 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0248. Min Act: -0.0006

Data Index: 683411 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0238. Min Act: -0.0006

Data Index: 161986 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1012100 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1027596 (C4 (Web Text))

Max Activating Token Index: 389