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

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

Neuron 3661 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1036219 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.2260. Min Act: -0.0000

Data Index: 939527 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1072425 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.0997. Min Act: -0.0000

Data Index: 78024 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.1556. Min Act: -0.0000

Data Index: 335664 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.1582. Min Act: -0.0000

Data Index: 182860 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.1575. Min Act: -0.0000

Data Index: 438260 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.0639. Min Act: -0.0000

Data Index: 664038 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.2560. Min Act: -0.0000

Data Index: 638799 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.0588. Min Act: -0.0000

Data Index: 928599 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.0836. Min Act: -0.0000

Data Index: 349426 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.0547. Min Act: -0.0000

Data Index: 208066 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.0577. Min Act: -0.0000

Data Index: 29819 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.2560. Min Range: -1.2560

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1556987 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.0655. Min Act: -0.0000

Data Index: 584773 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.2560. Min Range: -1.2560

Max Act: 0.9509. Min Act: -0.0000

Data Index: 166437 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.2013. Min Act: -0.0000

Data Index: 695988 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.2560. Min Range: -1.2560

Max Act: 1.0089. Min Act: -0.0000

Data Index: 971540 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 1.2560. Min Range: -1.2560

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1162227 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 1.2560. Min Range: -1.2560

Max Act: 0.8918. Min Act: -0.0000

Data Index: 385671 (C4 (Web Text))

Max Activating Token Index: 206