Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4859 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0706. Min Act: -0.0003

Data Index: 841000 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1212719 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0715. Min Act: -0.0002

Data Index: 464833 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0656. Min Act: -0.0002

Data Index: 912474 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0616. Min Act: -0.0003

Data Index: 282635 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0632. Min Act: -0.0003

Data Index: 595106 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0636. Min Act: -0.0003

Data Index: 335176 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1196574 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0618. Min Act: -0.0003

Data Index: 719200 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0618. Min Act: -0.0003

Data Index: 610744 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0607. Min Act: -0.0002

Data Index: 73017 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0583. Min Act: -0.0003

Data Index: 133060 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0594. Min Act: -0.0003

Data Index: 191831 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1039263 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1030432 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0595. Min Act: -0.0003

Data Index: 217458 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1228078 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0586. Min Act: -0.0002

Data Index: 70474 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1065026 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0577. Min Act: -0.0003

Data Index: 809358 (C4 (Web Text))

Max Activating Token Index: 441