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

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

Neuron 3821 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0746. Min Act: -0.0002

Data Index: 626919 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0672. Min Act: -0.0002

Data Index: 664461 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1095226 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1417056 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0634. Min Act: -0.0002

Data Index: 615883 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0625. Min Act: -0.0002

Data Index: 602760 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0618. Min Act: -0.0002

Data Index: 896324 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0615. Min Act: -0.0002

Data Index: 341225 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1647288 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0581. Min Act: -0.0002

Data Index: 397066 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1308726 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0592. Min Act: -0.0002

Data Index: 496319 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1303309 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1335569 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0563. Min Act: -0.0002

Data Index: 684201 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0622. Min Act: -0.0002

Data Index: 518757 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0576. Min Act: -0.0002

Data Index: 394027 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0569. Min Act: -0.0003

Data Index: 737417 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0526. Min Act: -0.0002

Data Index: 362806 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1286186 (C4 (Web Text))

Max Activating Token Index: 992