Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4083 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0017. Min Act: -0.0003

Data Index: 132294 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1648012 (Python Code)

Max Activating Token Index: 372

Text #2

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0014. Min Act: -0.0003

Data Index: 940292 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0013. Min Act: -0.0002

Data Index: 1459046 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1481684 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1482427 (Python Code)

Max Activating Token Index: 698

Text #6

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1454272 (Python Code)

Max Activating Token Index: 167

Text #7

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1510522 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0011. Min Act: -0.0003

Data Index: 806197 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0011. Min Act: -0.0002

Data Index: 874761 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1382761 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1642409 (Python Code)

Max Activating Token Index: 710

Text #12

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1433542 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1522434 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0010. Min Act: -0.0003

Data Index: 1437241 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1409612 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1401100 (Python Code)

Max Activating Token Index: 401

Text #17

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0011. Min Act: -0.0003

Data Index: 519891 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1644645 (Python Code)

Max Activating Token Index: 642

Text #19

Max Range: 0.0017. Min Range: -0.0017

Max Act: 0.0010. Min Act: -0.0003

Data Index: 522144 (C4 (Web Text))

Max Activating Token Index: 852