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

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

Neuron 536 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: 1.8508. Min Range: -1.8508

Max Act: 1.8508. Min Act: 0.0000

Data Index: 862916 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.8123. Min Act: -0.0000

Data Index: 975787 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.6231. Min Act: -0.0000

Data Index: 225661 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.6441. Min Act: -0.0000

Data Index: 862719 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.6432. Min Act: -0.0000

Data Index: 211209 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.6819. Min Act: -0.0000

Data Index: 218013 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7441. Min Act: -0.0000

Data Index: 805914 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.6375. Min Act: -0.0000

Data Index: 129726 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.6998. Min Act: -0.0000

Data Index: 535407 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.6270. Min Act: -0.0000

Data Index: 208491 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.5156. Min Act: -0.0000

Data Index: 1057850 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.5583. Min Act: -0.0000

Data Index: 247625 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1245160 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.4818. Min Act: -0.0000

Data Index: 629795 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1019763 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.3575. Min Act: -0.0000

Data Index: 1021958 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.4941. Min Act: -0.0000

Data Index: 168575 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1020955 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.4299. Min Act: -0.0000

Data Index: 1315744 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1159042 (C4 (Web Text))

Max Activating Token Index: 58