Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2013 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0618. Min Act: -0.0003

Data Index: 382537 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0616. Min Act: -0.0003

Data Index: 587681 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0003

Data Index: 494586 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0596. Min Act: -0.0003

Data Index: 674858 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0585. Min Act: -0.0003

Data Index: 362371 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0607. Min Act: -0.0003

Data Index: 756011 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0591. Min Act: -0.0003

Data Index: 280611 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0600. Min Act: -0.0003

Data Index: 291548 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0580. Min Act: -0.0002

Data Index: 446876 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0577. Min Act: -0.0004

Data Index: 703268 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0572. Min Act: -0.0003

Data Index: 679065 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0576. Min Act: -0.0003

Data Index: 391042 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0563. Min Act: -0.0002

Data Index: 76228 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0566. Min Act: -0.0003

Data Index: 1238615 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0566. Min Act: -0.0003

Data Index: 550399 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0570. Min Act: -0.0003

Data Index: 765148 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1021268 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0540. Min Act: -0.0002

Data Index: 487608 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0551. Min Act: -0.0002

Data Index: 241990 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0546. Min Act: -0.0002

Data Index: 288511 (C4 (Web Text))

Max Activating Token Index: 421