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

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

Neuron 390 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: 0.0783. Min Range: -0.0783

Max Act: 0.0783. Min Act: -0.0002

Data Index: 84271 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1990 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0662. Min Act: -0.0002

Data Index: 296543 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0574. Min Act: -0.0002

Data Index: 108723 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0633. Min Act: -0.0002

Data Index: 338696 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0559. Min Act: -0.0002

Data Index: 122867 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0610. Min Act: -0.0002

Data Index: 79150 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0580. Min Act: -0.0002

Data Index: 678916 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0599. Min Act: -0.0002

Data Index: 703458 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1312592 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0572. Min Act: -0.0002

Data Index: 511549 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1194470 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0585. Min Act: -0.0002

Data Index: 859905 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0624. Min Act: -0.0002

Data Index: 222372 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0598. Min Act: -0.0002

Data Index: 848782 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0555. Min Act: -0.0002

Data Index: 343584 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0524. Min Act: -0.0002

Data Index: 203752 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0507. Min Act: -0.0002

Data Index: 254688 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0507. Min Act: -0.0002

Data Index: 773828 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0557. Min Act: -0.0002

Data Index: 12427 (C4 (Web Text))

Max Activating Token Index: 737