Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 21 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0959. Min Act: -0.0001

Data Index: 1086794 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0339. Min Act: -0.0001

Data Index: 1648596 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9308. Min Act: -0.0001

Data Index: 1524359 (Python Code)

Max Activating Token Index: 653

Text #3

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9486. Min Act: -0.0001

Data Index: 1416260 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9648. Min Act: -0.0001

Data Index: 1568733 (Python Code)

Max Activating Token Index: 795

Text #5

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9394. Min Act: -0.0001

Data Index: 459962 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9221. Min Act: -0.0001

Data Index: 1634273 (Python Code)

Max Activating Token Index: 217

Text #7

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9493. Min Act: -0.0001

Data Index: 648999 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9252. Min Act: -0.0001

Data Index: 1365226 (Python Code)

Max Activating Token Index: 516

Text #9

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.8831. Min Act: -0.0001

Data Index: 1535911 (Python Code)

Max Activating Token Index: 871

Text #10

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1517953 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9290. Min Act: -0.0001

Data Index: 1468913 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9823. Min Act: -0.0001

Data Index: 1390369 (Python Code)

Max Activating Token Index: 677

Text #13

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.8867. Min Act: -0.0001

Data Index: 1644886 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1419277 (Python Code)

Max Activating Token Index: 594

Text #15

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9326. Min Act: -0.0001

Data Index: 1416626 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9226. Min Act: -0.0001

Data Index: 1629390 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.8924. Min Act: -0.0001

Data Index: 1532499 (Python Code)

Max Activating Token Index: 480

Text #18

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.9164. Min Act: -0.0001

Data Index: 1471772 (Python Code)

Max Activating Token Index: 358

Text #19

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.8909. Min Act: -0.0001

Data Index: 1376938 (Python Code)

Max Activating Token Index: 553