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

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

Neuron 3082 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0002

Data Index: 507190 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0620. Min Act: -0.0002

Data Index: 551115 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0685. Min Act: -0.0002

Data Index: 374698 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0726. Min Act: -0.0002

Data Index: 397975 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0562. Min Act: -0.0002

Data Index: 145110 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0602. Min Act: -0.0002

Data Index: 109679 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0653. Min Act: -0.0002

Data Index: 119005 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1005579 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0713. Min Act: -0.0002

Data Index: 147646 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0585. Min Act: -0.0002

Data Index: 225665 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1076041 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0564. Min Act: -0.0002

Data Index: 130697 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1019484 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0618. Min Act: -0.0002

Data Index: 247500 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0614. Min Act: -0.0002

Data Index: 713891 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1083801 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0571. Min Act: -0.0002

Data Index: 548876 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0590. Min Act: -0.0002

Data Index: 211446 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0604. Min Act: -0.0002

Data Index: 167899 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0606. Min Act: -0.0002

Data Index: 555818 (C4 (Web Text))

Max Activating Token Index: 157