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

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

Neuron 4069 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.4107. Min Act: -0.0001

Data Index: 187197 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.4678. Min Act: -0.0001

Data Index: 1017596 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.3662. Min Act: -0.0001

Data Index: 1352537 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.2392. Min Act: -0.0001

Data Index: 462072 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.2879. Min Act: -0.0001

Data Index: 400784 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.3351. Min Act: -0.0001

Data Index: 1049994 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.3242. Min Act: -0.0001

Data Index: 1019071 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.2373. Min Act: -0.0001

Data Index: 160413 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.2644. Min Act: -0.0001

Data Index: 40717 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.3340. Min Act: -0.0001

Data Index: 1157902 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.1945. Min Act: -0.0001

Data Index: 976241 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.1830. Min Act: -0.0001

Data Index: 234326 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.2083. Min Act: -0.0001

Data Index: 439490 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.1553. Min Act: -0.0001

Data Index: 95127 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.2767. Min Act: -0.0001

Data Index: 845262 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.1827. Min Act: -0.0001

Data Index: 296063 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.0413. Min Act: -0.0001

Data Index: 951314 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.2024. Min Act: -0.0001

Data Index: 645515 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.0569. Min Act: -0.0001

Data Index: 451694 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.4678. Min Range: -1.4678

Max Act: 1.1573. Min Act: -0.0001

Data Index: 893657 (C4 (Web Text))

Max Activating Token Index: 316