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

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

Neuron 4621 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1024609 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1222501 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.7008. Min Act: -0.0000

Data Index: 237823 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1193959 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6926. Min Act: -0.0000

Data Index: 967231 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1152705 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1002910 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6652. Min Act: -0.0000

Data Index: 548462 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1272676 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6368. Min Act: -0.0000

Data Index: 992927 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6168. Min Act: -0.0000

Data Index: 236313 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6078. Min Act: -0.0000

Data Index: 165097 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6279. Min Act: -0.0000

Data Index: 816479 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6069. Min Act: -0.0000

Data Index: 636255 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6368. Min Act: -0.0000

Data Index: 442799 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.5889. Min Act: -0.0000

Data Index: 748669 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6051. Min Act: -0.0000

Data Index: 251345 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.5888. Min Act: -0.0000

Data Index: 360118 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.5879. Min Act: -0.0000

Data Index: 412512 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.9754. Min Range: -0.9754

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1150111 (C4 (Web Text))

Max Activating Token Index: 672