Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4203 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1262053 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0298. Min Act: -0.0001

Data Index: 790409 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0292. Min Act: -0.0001

Data Index: 866563 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1561231 (Python Code)

Max Activating Token Index: 452

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0276. Min Act: -0.0001

Data Index: 588785 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0277. Min Act: -0.0001

Data Index: 319410 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1332675 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1280572 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0263. Min Act: -0.0001

Data Index: 560121 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0265. Min Act: -0.0001

Data Index: 384272 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0265. Min Act: -0.0001

Data Index: 5621 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0259. Min Act: -0.0001

Data Index: 286796 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0238. Min Act: -0.0001

Data Index: 469253 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0251. Min Act: -0.0001

Data Index: 166308 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0240. Min Act: -0.0001

Data Index: 206476 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1243447 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0242. Min Act: -0.0001

Data Index: 202095 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1474364 (Python Code)

Max Activating Token Index: 707

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1303865 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0243. Min Act: -0.0001

Data Index: 178409 (C4 (Web Text))

Max Activating Token Index: 718