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

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

Neuron 2111 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: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0004

Data Index: 239679 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0289. Min Act: -0.0004

Data Index: 199938 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0223. Min Act: -0.0004

Data Index: 825303 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0263. Min Act: -0.0004

Data Index: 939824 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0286. Min Act: -0.0004

Data Index: 431551 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0246. Min Act: -0.0004

Data Index: 802386 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0239. Min Act: -0.0004

Data Index: 248050 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1257487 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0216. Min Act: -0.0004

Data Index: 1121434 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0251. Min Act: -0.0004

Data Index: 130328 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0251. Min Act: -0.0004

Data Index: 341757 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0250. Min Act: -0.0004

Data Index: 750590 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0219. Min Act: -0.0004

Data Index: 1349532 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0274. Min Act: -0.0004

Data Index: 765078 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0200. Min Act: -0.0004

Data Index: 1483274 (Python Code)

Max Activating Token Index: 615

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0264. Min Act: -0.0004

Data Index: 642739 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0263. Min Act: -0.0004

Data Index: 847576 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0219. Min Act: -0.0004

Data Index: 1195927 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0192. Min Act: -0.0004

Data Index: 446885 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1346584 (C4 (Web Text))

Max Activating Token Index: 836