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

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

Neuron 1526 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5476. Min Act: -0.0000

Data Index: 587364 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.6121. Min Act: -0.0001

Data Index: 816411 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5200. Min Act: -0.0001

Data Index: 113011 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5511. Min Act: -0.0001

Data Index: 577485 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4655. Min Act: -0.0000

Data Index: 394910 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1067643 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4237. Min Act: -0.0001

Data Index: 1650675 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4684. Min Act: -0.0001

Data Index: 1059022 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4232. Min Act: -0.0001

Data Index: 641767 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4571. Min Act: -0.0000

Data Index: 462674 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4206. Min Act: -0.0000

Data Index: 567314 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4195. Min Act: -0.0000

Data Index: 851432 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4253. Min Act: -0.0001

Data Index: 108579 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4073. Min Act: -0.0000

Data Index: 221284 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1519891 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4004. Min Act: -0.0000

Data Index: 583379 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1145836 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.3901. Min Act: -0.0001

Data Index: 1258664 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.3846. Min Act: -0.0000

Data Index: 515920 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.3802. Min Act: -0.0000

Data Index: 33038 (C4 (Web Text))

Max Activating Token Index: 770