Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 34 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0729. Min Act: -0.0004

Data Index: 284611 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0741. Min Act: -0.0003

Data Index: 396695 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0731. Min Act: -0.0003

Data Index: 388353 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0700. Min Act: -0.0002

Data Index: 661601 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1324658 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1092197 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1312057 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0653. Min Act: -0.0003

Data Index: 214429 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0652. Min Act: -0.0003

Data Index: 401881 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0628. Min Act: -0.0003

Data Index: 671677 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0661. Min Act: -0.0003

Data Index: 819530 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0639. Min Act: -0.0002

Data Index: 874136 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0635. Min Act: -0.0003

Data Index: 685245 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0649. Min Act: -0.0002

Data Index: 353161 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0617. Min Act: -0.0003

Data Index: 631437 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0654. Min Act: -0.0002

Data Index: 744325 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1153923 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0621. Min Act: -0.0003

Data Index: 309119 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1092494 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1256710 (C4 (Web Text))

Max Activating Token Index: 443