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

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

Neuron 3566 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1401558 (Python Code)

Max Activating Token Index: 206

Text #1

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.7415. Min Act: -0.0000

Data Index: 825722 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1631989 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6219. Min Act: -0.0000

Data Index: 27072 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1643100 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6168. Min Act: -0.0000

Data Index: 999041 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5809. Min Act: -0.0000

Data Index: 57502 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1600842 (Python Code)

Max Activating Token Index: 100

Text #8

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1650219 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1443971 (Python Code)

Max Activating Token Index: 285

Text #10

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1449997 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1605681 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1436572 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1569950 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1385695 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1367542 (Python Code)

Max Activating Token Index: 333

Text #16

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4959. Min Act: -0.0000

Data Index: 56451 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1535774 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1108584 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1587828 (Python Code)

Max Activating Token Index: 134