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

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

Neuron 3816 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1226517 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1134911 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0744. Min Act: -0.0001

Data Index: 69379 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0787. Min Act: -0.0001

Data Index: 68475 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1576691 (Python Code)

Max Activating Token Index: 700

Text #5

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0731. Min Act: -0.0001

Data Index: 939289 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0763. Min Act: -0.0001

Data Index: 991382 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0701. Min Act: -0.0001

Data Index: 831019 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0704. Min Act: -0.0001

Data Index: 880483 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0699. Min Act: -0.0001

Data Index: 218971 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1357815 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1623508 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1401156 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1583567 (Python Code)

Max Activating Token Index: 387

Text #14

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1562905 (Python Code)

Max Activating Token Index: 257

Text #15

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0629. Min Act: -0.0001

Data Index: 387454 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0611. Min Act: -0.0001

Data Index: 131228 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1608708 (Python Code)

Max Activating Token Index: 593

Text #18

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1533482 (Python Code)

Max Activating Token Index: 848

Text #19

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0571. Min Act: -0.0001

Data Index: 248759 (C4 (Web Text))

Max Activating Token Index: 424