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

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

Neuron 212 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0741. Min Act: -0.0002

Data Index: 464459 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0741. Min Act: -0.0002

Data Index: 186269 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0002

Data Index: 813301 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0728. Min Act: -0.0002

Data Index: 865327 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0692. Min Act: -0.0002

Data Index: 777825 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1268465 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0689. Min Act: -0.0002

Data Index: 954234 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0688. Min Act: -0.0002

Data Index: 914387 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1097316 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1188628 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0630. Min Act: -0.0002

Data Index: 920661 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0642. Min Act: -0.0002

Data Index: 893528 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0633. Min Act: -0.0002

Data Index: 277633 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1046187 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0613. Min Act: -0.0002

Data Index: 436212 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0648. Min Act: -0.0002

Data Index: 336176 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1073384 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0586. Min Act: -0.0002

Data Index: 873087 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1069590 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1100467 (C4 (Web Text))

Max Activating Token Index: 99