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

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

Neuron 7 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: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1590138 (Python Code)

Max Activating Token Index: 392

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1613867 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1587272 (Python Code)

Max Activating Token Index: 999

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1468493 (Python Code)

Max Activating Token Index: 624

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0311. Min Act: -0.0003

Data Index: 288698 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1379306 (Python Code)

Max Activating Token Index: 734

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1421344 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1479479 (Python Code)

Max Activating Token Index: 323

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0280. Min Act: -0.0003

Data Index: 238700 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0288. Min Act: -0.0004

Data Index: 1174030 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1643609 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0270. Min Act: -0.0004

Data Index: 1550937 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1375034 (Python Code)

Max Activating Token Index: 437

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1592852 (Python Code)

Max Activating Token Index: 265

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0271. Min Act: -0.0004

Data Index: 904061 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1625885 (Python Code)

Max Activating Token Index: 610

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1643834 (Python Code)

Max Activating Token Index: 569

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1320131 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0257. Min Act: -0.0003

Data Index: 462080 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1541203 (Python Code)

Max Activating Token Index: 377