Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1834 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0003

Data Index: 685965 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1151268 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0723. Min Act: -0.0004

Data Index: 349835 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1035442 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0648. Min Act: -0.0003

Data Index: 83042 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0637. Min Act: -0.0003

Data Index: 370401 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1240295 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0623. Min Act: -0.0003

Data Index: 17641 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0594. Min Act: -0.0003

Data Index: 989045 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0594. Min Act: -0.0003

Data Index: 95440 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1013486 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0593. Min Act: -0.0003

Data Index: 383701 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0588. Min Act: -0.0003

Data Index: 767755 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0587. Min Act: -0.0003

Data Index: 734247 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1039485 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0597. Min Act: -0.0003

Data Index: 997559 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0572. Min Act: -0.0003

Data Index: 309047 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0561. Min Act: -0.0003

Data Index: 174637 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0635. Min Act: -0.0003

Data Index: 739457 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1325688 (C4 (Web Text))

Max Activating Token Index: 387