Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3457 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0988. Min Act: -0.0000

Data Index: 802819 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1634027 (Python Code)

Max Activating Token Index: 663

Text #2

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1154511 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1384572 (Python Code)

Max Activating Token Index: 302

Text #4

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1579067 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1650084 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0875. Min Act: -0.0000

Data Index: 786795 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0791. Min Act: -0.0000

Data Index: 6207 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0807. Min Act: -0.0000

Data Index: 592413 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1486589 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0803. Min Act: -0.0000

Data Index: 702487 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1165940 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0734. Min Act: -0.0000

Data Index: 2809 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1266352 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1631746 (Python Code)

Max Activating Token Index: 911

Text #15

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1530002 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1380506 (Python Code)

Max Activating Token Index: 825

Text #17

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0732. Min Act: -0.0000

Data Index: 197656 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0733. Min Act: -0.0000

Data Index: 11956 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0766. Min Act: -0.0000

Data Index: 183997 (C4 (Web Text))

Max Activating Token Index: 600