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

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

Neuron 3380 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1628548 (Python Code)

Max Activating Token Index: 994

Text #1

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1692. Min Act: -0.0000

Data Index: 431441 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1004838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1376603 (Python Code)

Max Activating Token Index: 594

Text #4

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1479294 (Python Code)

Max Activating Token Index: 609

Text #5

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1265837 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1397636 (Python Code)

Max Activating Token Index: 770

Text #7

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1204826 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1471084 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1397519 (Python Code)

Max Activating Token Index: 315

Text #10

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1382583 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1557415 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1374577 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1593058 (Python Code)

Max Activating Token Index: 698

Text #14

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1619255 (Python Code)

Max Activating Token Index: 1017

Text #15

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1206. Min Act: -0.0000

Data Index: 573372 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1405737 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1462292 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1559208 (Python Code)

Max Activating Token Index: 508

Text #19

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1165. Min Act: -0.0000

Data Index: 185070 (C4 (Web Text))

Max Activating Token Index: 1003