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

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

Neuron 3420 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3668. Min Act: -0.0000

Data Index: 52916 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3235. Min Act: -0.0000

Data Index: 712915 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1116997 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2701. Min Act: -0.0000

Data Index: 177454 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1025268 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2646. Min Act: -0.0000

Data Index: 949852 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1334638 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1259556 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2375. Min Act: -0.0000

Data Index: 469290 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1289010 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2453. Min Act: -0.0000

Data Index: 997279 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2320. Min Act: -0.0000

Data Index: 871013 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2308. Min Act: -0.0000

Data Index: 483189 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2390. Min Act: -0.0000

Data Index: 704906 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2454. Min Act: -0.0000

Data Index: 364145 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2236. Min Act: -0.0000

Data Index: 406346 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2232. Min Act: -0.0000

Data Index: 655497 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2214. Min Act: -0.0000

Data Index: 907932 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1003709 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2274. Min Act: -0.0000

Data Index: 522268 (C4 (Web Text))

Max Activating Token Index: 864