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

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

Neuron 760 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: 1.1067. Min Range: -1.1067

Max Act: 1.1013. Min Act: -0.0001

Data Index: 1113132 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.1067. Min Act: -0.0001

Data Index: 441944 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.0611. Min Act: -0.0001

Data Index: 1095581 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.0606. Min Act: -0.0001

Data Index: 282117 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.0146. Min Act: -0.0001

Data Index: 1347051 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.0300. Min Act: -0.0001

Data Index: 579052 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.0149. Min Act: -0.0001

Data Index: 713321 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.0345. Min Act: -0.0001

Data Index: 918608 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9687. Min Act: -0.0001

Data Index: 182340 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 1.1067. Min Range: -1.1067

Max Act: 1.0332. Min Act: -0.0001

Data Index: 844474 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9818. Min Act: -0.0001

Data Index: 1150898 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9745. Min Act: -0.0001

Data Index: 229462 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9057. Min Act: -0.0001

Data Index: 605130 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9670. Min Act: -0.0001

Data Index: 226100 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9622. Min Act: -0.0001

Data Index: 160897 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9665. Min Act: -0.0001

Data Index: 314178 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9235. Min Act: -0.0001

Data Index: 1231168 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9566. Min Act: -0.0001

Data Index: 1033868 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9484. Min Act: -0.0001

Data Index: 50671 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.1067. Min Range: -1.1067

Max Act: 0.9450. Min Act: -0.0001

Data Index: 1205190 (C4 (Web Text))

Max Activating Token Index: 651