Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 845 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0762. Min Act: -0.0003

Data Index: 545992 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1289751 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0734. Min Act: -0.0003

Data Index: 650733 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0741. Min Act: -0.0003

Data Index: 462213 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0699. Min Act: -0.0003

Data Index: 575832 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0689. Min Act: -0.0003

Data Index: 767361 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0681. Min Act: -0.0003

Data Index: 678637 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0648. Min Act: -0.0003

Data Index: 120952 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1270050 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0634. Min Act: -0.0003

Data Index: 174208 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0658. Min Act: -0.0003

Data Index: 914405 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0622. Min Act: -0.0003

Data Index: 970966 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0600. Min Act: -0.0003

Data Index: 308420 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0590. Min Act: -0.0003

Data Index: 180264 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0612. Min Act: -0.0003

Data Index: 469972 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0592. Min Act: -0.0003

Data Index: 737498 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0546. Min Act: -0.0003

Data Index: 488219 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0577. Min Act: -0.0003

Data Index: 1332237 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0559. Min Act: -0.0003

Data Index: 545751 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0563. Min Act: -0.0003

Data Index: 98002 (C4 (Web Text))

Max Activating Token Index: 662