Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 504 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1204696 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0739. Min Act: -0.0001

Data Index: 838393 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1111277 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0706. Min Act: -0.0001

Data Index: 180393 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0762. Min Act: -0.0001

Data Index: 841647 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0674. Min Act: -0.0001

Data Index: 409919 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0638. Min Act: -0.0001

Data Index: 339070 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0629. Min Act: -0.0001

Data Index: 359050 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0675. Min Act: -0.0001

Data Index: 510702 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0693. Min Act: -0.0001

Data Index: 217167 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0656. Min Act: -0.0001

Data Index: 552462 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0659. Min Act: -0.0001

Data Index: 567137 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0607. Min Act: -0.0001

Data Index: 362425 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0628. Min Act: -0.0001

Data Index: 333413 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0666. Min Act: -0.0001

Data Index: 308790 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1346249 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1345486 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0620. Min Act: -0.0001

Data Index: 873355 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0637. Min Act: -0.0001

Data Index: 658743 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1269669 (C4 (Web Text))

Max Activating Token Index: 36