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

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

Neuron 3237 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0003

Data Index: 748647 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0680. Min Act: -0.0003

Data Index: 992126 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0672. Min Act: -0.0003

Data Index: 327509 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0662. Min Act: -0.0003

Data Index: 46540 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0589. Min Act: -0.0003

Data Index: 496906 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0604. Min Act: -0.0003

Data Index: 418487 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1223792 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0622. Min Act: -0.0002

Data Index: 933788 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0582. Min Act: -0.0003

Data Index: 701980 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0568. Min Act: -0.0002

Data Index: 136315 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0549. Min Act: -0.0003

Data Index: 647170 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1307318 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0533. Min Act: -0.0002

Data Index: 914094 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0568. Min Act: -0.0003

Data Index: 447184 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1192135 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0553. Min Act: -0.0003

Data Index: 859044 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0512. Min Act: -0.0003

Data Index: 112222 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0532. Min Act: -0.0002

Data Index: 264680 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0501. Min Act: -0.0003

Data Index: 486872 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0495. Min Act: -0.0003

Data Index: 319051 (C4 (Web Text))

Max Activating Token Index: 658