Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1354 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0743. Min Act: -0.0002

Data Index: 342132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0675. Min Act: -0.0002

Data Index: 933821 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1338825 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0613. Min Act: -0.0002

Data Index: 411840 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0592. Min Act: -0.0002

Data Index: 307804 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0569. Min Act: -0.0002

Data Index: 847303 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1240581 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0563. Min Act: -0.0002

Data Index: 542275 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0562. Min Act: -0.0002

Data Index: 5055 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0556. Min Act: -0.0002

Data Index: 507180 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0537. Min Act: -0.0002

Data Index: 497436 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1053516 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1144457 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1164026 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1244609 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1167606 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1000420 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0532. Min Act: -0.0002

Data Index: 780973 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0517. Min Act: -0.0002

Data Index: 754615 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0524. Min Act: -0.0002

Data Index: 601223 (C4 (Web Text))

Max Activating Token Index: 808