Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 231 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0003

Data Index: 821440 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1375955 (Python Code)

Max Activating Token Index: 863

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1597300 (Python Code)

Max Activating Token Index: 644

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1384182 (Python Code)

Max Activating Token Index: 711

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1310504 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0302. Min Act: -0.0004

Data Index: 1649325 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0307. Min Act: -0.0002

Data Index: 84998 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1281789 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1416155 (Python Code)

Max Activating Token Index: 1006

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0302. Min Act: -0.0002

Data Index: 324945 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1297735 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0273. Min Act: -0.0003

Data Index: 379501 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1180771 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0300. Min Act: -0.0003

Data Index: 358843 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0283. Min Act: -0.0003

Data Index: 563454 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0286. Min Act: -0.0003

Data Index: 928823 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1448557 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1613889 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1445419 (Python Code)

Max Activating Token Index: 870

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0286. Min Act: -0.0003

Data Index: 246124 (C4 (Web Text))

Max Activating Token Index: 322