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

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

Neuron 4002 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: 0.0743. Min Range: -0.0743

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1499626 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0721. Min Act: -0.0002

Data Index: 949502 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0657. Min Act: -0.0002

Data Index: 689724 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1429478 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1617324 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1461866 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1481140 (Python Code)

Max Activating Token Index: 786

Text #7

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1576500 (Python Code)

Max Activating Token Index: 740

Text #8

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1593560 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1512482 (Python Code)

Max Activating Token Index: 683

Text #10

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1633887 (Python Code)

Max Activating Token Index: 837

Text #11

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1083290 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1285441 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1424296 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1559020 (Python Code)

Max Activating Token Index: 202

Text #15

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1549696 (Python Code)

Max Activating Token Index: 672

Text #16

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1551114 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1564817 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1458822 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1150697 (C4 (Web Text))

Max Activating Token Index: 390