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

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

Neuron 4778 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1093789 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7902. Min Act: -0.0000

Data Index: 355968 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.8047. Min Act: -0.0000

Data Index: 179507 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1067567 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7284. Min Act: -0.0000

Data Index: 855976 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7253. Min Act: -0.0000

Data Index: 989527 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1296446 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6753. Min Act: -0.0000

Data Index: 168051 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6778. Min Act: -0.0000

Data Index: 677147 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1203553 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1011361 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5929. Min Act: -0.0000

Data Index: 968758 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1105987 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1023317 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5627. Min Act: -0.0000

Data Index: 826670 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5353. Min Act: -0.0000

Data Index: 642941 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5228. Min Act: -0.0000

Data Index: 648219 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1147142 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5129. Min Act: -0.0000

Data Index: 344017 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1055206 (C4 (Web Text))

Max Activating Token Index: 164