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

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

Neuron 4848 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0002

Data Index: 305802 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1035715 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1009960 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0263. Min Act: -0.0002

Data Index: 333786 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0261. Min Act: -0.0002

Data Index: 765539 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1088199 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0259. Min Act: -0.0002

Data Index: 19897 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1055654 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1464235 (Python Code)

Max Activating Token Index: 743

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0247. Min Act: -0.0002

Data Index: 132752 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1561273 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0253. Min Act: -0.0002

Data Index: 54329 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0248. Min Act: -0.0002

Data Index: 165650 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1568655 (Python Code)

Max Activating Token Index: 880

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0239. Min Act: -0.0002

Data Index: 385969 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0232. Min Act: -0.0002

Data Index: 260327 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1099384 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0249. Min Act: -0.0002

Data Index: 818796 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0231. Min Act: -0.0002

Data Index: 68536 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1522224 (Python Code)

Max Activating Token Index: 189