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

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

Neuron 1608 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0275. Min Act: -0.0004

Data Index: 714227 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1338561 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1335769 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0266. Min Act: -0.0004

Data Index: 200390 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1325910 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0258. Min Act: -0.0004

Data Index: 522372 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0224. Min Act: -0.0004

Data Index: 48976 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0244. Min Act: -0.0004

Data Index: 998884 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0221. Min Act: -0.0004

Data Index: 853586 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0272. Min Act: -0.0004

Data Index: 1068631 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0268. Min Act: -0.0004

Data Index: 371282 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0285. Min Act: -0.0004

Data Index: 73457 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0216. Min Act: -0.0004

Data Index: 1213010 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0292. Min Act: -0.0004

Data Index: 1299865 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0249. Min Act: -0.0004

Data Index: 245885 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0267. Min Act: -0.0004

Data Index: 563430 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0284. Min Act: -0.0004

Data Index: 169949 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0261. Min Act: -0.0004

Data Index: 1014934 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0260. Min Act: -0.0004

Data Index: 586125 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0244. Min Act: -0.0004

Data Index: 504093 (C4 (Web Text))

Max Activating Token Index: 861