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

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

Neuron 132 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.9570. Min Act: -0.0000

Data Index: 709381 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.9237. Min Act: -0.0000

Data Index: 182243 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.7145. Min Act: -0.0000

Data Index: 853892 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.8126. Min Act: -0.0000

Data Index: 714875 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.5902. Min Act: -0.0000

Data Index: 1030250 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.5538. Min Act: -0.0000

Data Index: 518443 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1254614 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.6791. Min Act: -0.0000

Data Index: 907133 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.5712. Min Act: -0.0000

Data Index: 142893 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.5176. Min Act: -0.0000

Data Index: 423123 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.5967. Min Act: -0.0000

Data Index: 297801 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.5016. Min Act: -0.0000

Data Index: 963279 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.5155. Min Act: -0.0000

Data Index: 568935 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1227600 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.6617. Min Act: -0.0000

Data Index: 112126 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.5145. Min Act: -0.0000

Data Index: 63330 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.5337. Min Act: -0.0000

Data Index: 92382 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.4062. Min Act: -0.0000

Data Index: 34949 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.3937. Min Act: -0.0000

Data Index: 478409 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 1.9570. Min Range: -1.9570

Max Act: 1.4209. Min Act: -0.0000

Data Index: 136713 (C4 (Web Text))

Max Activating Token Index: 282