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

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

Neuron 347 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0003

Data Index: 513548 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0709. Min Act: -0.0003

Data Index: 849731 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0758. Min Act: -0.0003

Data Index: 111776 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0730. Min Act: -0.0003

Data Index: 748313 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0707. Min Act: -0.0003

Data Index: 828267 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0683. Min Act: -0.0003

Data Index: 594855 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0712. Min Act: -0.0003

Data Index: 690163 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0618. Min Act: -0.0003

Data Index: 954361 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0655. Min Act: -0.0003

Data Index: 568344 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0687. Min Act: -0.0003

Data Index: 357829 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0705. Min Act: -0.0003

Data Index: 396475 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0690. Min Act: -0.0003

Data Index: 296058 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0705. Min Act: -0.0003

Data Index: 775877 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1100591 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1111796 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0683. Min Act: -0.0003

Data Index: 536253 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0694. Min Act: -0.0003

Data Index: 642647 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0681. Min Act: -0.0003

Data Index: 605879 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0670. Min Act: -0.0003

Data Index: 675598 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0681. Min Act: -0.0003

Data Index: 984426 (C4 (Web Text))

Max Activating Token Index: 968