Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 660 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0663. Min Act: -0.0003

Data Index: 647137 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0003

Data Index: 361294 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0663. Min Act: -0.0004

Data Index: 688153 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0665. Min Act: -0.0004

Data Index: 1174063 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1019319 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1054232 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0615. Min Act: -0.0004

Data Index: 777156 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0610. Min Act: -0.0003

Data Index: 265807 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0596. Min Act: -0.0003

Data Index: 953662 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0615. Min Act: -0.0003

Data Index: 612122 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0614. Min Act: -0.0003

Data Index: 191737 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0602. Min Act: -0.0003

Data Index: 130956 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0599. Min Act: -0.0003

Data Index: 523624 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0605. Min Act: -0.0004

Data Index: 1019796 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0588. Min Act: -0.0003

Data Index: 10084 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1030353 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0592. Min Act: -0.0004

Data Index: 727424 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0576. Min Act: -0.0004

Data Index: 483577 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0584. Min Act: -0.0003

Data Index: 908559 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0580. Min Act: -0.0004

Data Index: 978406 (C4 (Web Text))

Max Activating Token Index: 631