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

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

Neuron 4491 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: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0002

Data Index: 383271 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0715. Min Act: -0.0002

Data Index: 500066 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1158154 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0631. Min Act: -0.0003

Data Index: 375221 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0627. Min Act: -0.0003

Data Index: 651634 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0621. Min Act: -0.0003

Data Index: 616825 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0621. Min Act: -0.0002

Data Index: 993562 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0644. Min Act: -0.0003

Data Index: 221954 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0617. Min Act: -0.0002

Data Index: 438136 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0593. Min Act: -0.0002

Data Index: 933960 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1238318 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0587. Min Act: -0.0002

Data Index: 462650 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0599. Min Act: -0.0002

Data Index: 333451 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0589. Min Act: -0.0003

Data Index: 28619 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0576. Min Act: -0.0002

Data Index: 100281 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0551. Min Act: -0.0002

Data Index: 561370 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1093196 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0578. Min Act: -0.0002

Data Index: 504361 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1165448 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1070402 (C4 (Web Text))

Max Activating Token Index: 558