Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1038 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0005

Data Index: 125531 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0923. Min Act: -0.0005

Data Index: 33275 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0742. Min Act: -0.0005

Data Index: 587180 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0679. Min Act: -0.0005

Data Index: 164798 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0673. Min Act: -0.0005

Data Index: 954168 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0671. Min Act: -0.0005

Data Index: 618425 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0640. Min Act: -0.0004

Data Index: 518085 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0637. Min Act: -0.0005

Data Index: 1000421 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0646. Min Act: -0.0005

Data Index: 812623 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0628. Min Act: -0.0005

Data Index: 1165463 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0648. Min Act: -0.0005

Data Index: 578828 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0588. Min Act: -0.0005

Data Index: 86908 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0625. Min Act: -0.0005

Data Index: 243948 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0597. Min Act: -0.0005

Data Index: 1009010 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0644. Min Act: -0.0005

Data Index: 257895 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0595. Min Act: -0.0005

Data Index: 662161 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0698. Min Act: -0.0005

Data Index: 1125021 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0555. Min Act: -0.0005

Data Index: 797740 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0550. Min Act: -0.0005

Data Index: 47724 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0583. Min Act: -0.0005

Data Index: 1009389 (C4 (Web Text))

Max Activating Token Index: 58