Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2011 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.3490. Min Act: -0.0000

Data Index: 284420 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.3429. Min Act: -0.0000

Data Index: 226967 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.2063. Min Act: -0.0000

Data Index: 424032 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.2029. Min Act: -0.0000

Data Index: 1265940 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.2022. Min Act: -0.0000

Data Index: 211511 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1037072 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1266918 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1703. Min Act: -0.0000

Data Index: 550078 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1255005 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1358. Min Act: -0.0000

Data Index: 997382 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1346. Min Act: -0.0000

Data Index: 422691 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1023424 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1219. Min Act: -0.0000

Data Index: 805494 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.0675. Min Act: -0.0000

Data Index: 519849 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1162. Min Act: -0.0000

Data Index: 596212 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1359716 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1320748 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.0810. Min Act: -0.0000

Data Index: 916470 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 1.3490. Min Range: -1.3490

Max Act: 1.0624. Min Act: -0.0000

Data Index: 357802 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.3490. Min Range: -1.3490

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1230937 (C4 (Web Text))

Max Activating Token Index: 847