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

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

Neuron 876 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.8175. Min Act: -0.0003

Data Index: 768831 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.7076. Min Act: -0.0003

Data Index: 1251870 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.6687. Min Act: -0.0003

Data Index: 1162694 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.6287. Min Act: -0.0003

Data Index: 1303004 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5896. Min Act: -0.0003

Data Index: 1205287 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.6141. Min Act: -0.0003

Data Index: 398910 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5670. Min Act: -0.0003

Data Index: 160636 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5844. Min Act: -0.0003

Data Index: 755164 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5597. Min Act: -0.0003

Data Index: 1217500 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5708. Min Act: -0.0003

Data Index: 351542 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5650. Min Act: -0.0003

Data Index: 894107 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5690. Min Act: -0.0003

Data Index: 828253 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5601. Min Act: -0.0003

Data Index: 48155 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5621. Min Act: -0.0003

Data Index: 813609 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5229. Min Act: -0.0003

Data Index: 1162598 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4905. Min Act: -0.0003

Data Index: 717914 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4924. Min Act: -0.0002

Data Index: 333564 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5017. Min Act: -0.0003

Data Index: 1170307 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5018. Min Act: -0.0002

Data Index: 611900 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5031. Min Act: -0.0003

Data Index: 642695 (C4 (Web Text))

Max Activating Token Index: 624