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

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

Neuron 478 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0001

Data Index: 303477 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0298. Min Act: -0.0001

Data Index: 878985 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0320. Min Act: -0.0001

Data Index: 63886 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0294. Min Act: -0.0001

Data Index: 986017 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0273. Min Act: -0.0001

Data Index: 395594 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0265. Min Act: -0.0001

Data Index: 642865 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0255. Min Act: -0.0001

Data Index: 914106 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0262. Min Act: -0.0001

Data Index: 850991 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0246. Min Act: -0.0001

Data Index: 478779 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1088693 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0249. Min Act: -0.0001

Data Index: 181179 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1175610 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1003919 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0249. Min Act: -0.0001

Data Index: 683321 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0245. Min Act: -0.0001

Data Index: 976145 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0233. Min Act: -0.0001

Data Index: 360580 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1097379 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0236. Min Act: -0.0001

Data Index: 747021 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0205. Min Act: -0.0001

Data Index: 486445 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0191. Min Act: -0.0001

Data Index: 173065 (C4 (Web Text))

Max Activating Token Index: 270