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

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

Neuron 3945 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4756. Min Act: -0.0000

Data Index: 928874 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4628. Min Act: -0.0001

Data Index: 875361 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4733. Min Act: -0.0000

Data Index: 138173 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4193. Min Act: -0.0000

Data Index: 505176 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3859. Min Act: -0.0001

Data Index: 1233306 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1020983 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3791. Min Act: -0.0000

Data Index: 432215 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3811. Min Act: -0.0000

Data Index: 803770 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1060579 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3627. Min Act: -0.0000

Data Index: 700197 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3871. Min Act: -0.0000

Data Index: 158307 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3714. Min Act: -0.0000

Data Index: 383958 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1334672 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3816. Min Act: -0.0000

Data Index: 135872 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1324250 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3709. Min Act: -0.0000

Data Index: 766268 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3484. Min Act: -0.0000

Data Index: 982971 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3641. Min Act: -0.0000

Data Index: 651372 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3558. Min Act: -0.0000

Data Index: 919486 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1297405 (C4 (Web Text))

Max Activating Token Index: 479