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

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

Neuron 523 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: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0003

Data Index: 422247 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0594. Min Act: -0.0003

Data Index: 543850 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0600. Min Act: -0.0003

Data Index: 632145 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0590. Min Act: -0.0003

Data Index: 160975 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1282190 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0585. Min Act: -0.0004

Data Index: 429149 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0555. Min Act: -0.0004

Data Index: 651766 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0565. Min Act: -0.0003

Data Index: 780791 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0571. Min Act: -0.0003

Data Index: 234990 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0555. Min Act: -0.0003

Data Index: 902790 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0562. Min Act: -0.0003

Data Index: 434227 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1148026 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1175348 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0548. Min Act: -0.0003

Data Index: 743804 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0544. Min Act: -0.0003

Data Index: 423318 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1169101 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0540. Min Act: -0.0003

Data Index: 613792 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0539. Min Act: -0.0003

Data Index: 497309 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1113588 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0548. Min Act: -0.0004

Data Index: 288334 (C4 (Web Text))

Max Activating Token Index: 365