Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 165 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0866. Min Act: -0.0003

Data Index: 320762 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0667. Min Act: -0.0003

Data Index: 4813 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0663. Min Act: -0.0003

Data Index: 581435 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1251666 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1351514 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1082500 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0627. Min Act: -0.0003

Data Index: 91265 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0569. Min Act: -0.0003

Data Index: 966239 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0638. Min Act: -0.0003

Data Index: 784799 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0577. Min Act: -0.0003

Data Index: 1141800 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0646. Min Act: -0.0003

Data Index: 769169 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1043447 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0583. Min Act: -0.0003

Data Index: 666126 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0577. Min Act: -0.0003

Data Index: 730271 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0663. Min Act: -0.0003

Data Index: 843130 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0512. Min Act: -0.0003

Data Index: 40597 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1170178 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0562. Min Act: -0.0003

Data Index: 849142 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0571. Min Act: -0.0003

Data Index: 796203 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0547. Min Act: -0.0003

Data Index: 117160 (C4 (Web Text))

Max Activating Token Index: 808