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

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

Neuron 1027 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0698. Min Act: -0.0006

Data Index: 396648 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0677. Min Act: -0.0006

Data Index: 644574 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0659. Min Act: -0.0006

Data Index: 448654 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0659. Min Act: -0.0006

Data Index: 984235 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0675. Min Act: -0.0006

Data Index: 561099 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0006

Data Index: 1303396 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0644. Min Act: -0.0006

Data Index: 587606 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0632. Min Act: -0.0006

Data Index: 1211393 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0655. Min Act: -0.0006

Data Index: 944425 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0629. Min Act: -0.0006

Data Index: 232471 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0629. Min Act: -0.0006

Data Index: 597782 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0622. Min Act: -0.0005

Data Index: 396204 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0646. Min Act: -0.0006

Data Index: 1278347 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0643. Min Act: -0.0006

Data Index: 1275889 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0609. Min Act: -0.0006

Data Index: 85815 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0604. Min Act: -0.0006

Data Index: 532764 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0603. Min Act: -0.0006

Data Index: 553765 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0602. Min Act: -0.0006

Data Index: 105511 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0599. Min Act: -0.0006

Data Index: 430654 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0599. Min Act: -0.0006

Data Index: 61943 (C4 (Web Text))

Max Activating Token Index: 665