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

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

Neuron 243 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: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1024519 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1278415 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1096110 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0644. Min Act: -0.0002

Data Index: 256271 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0626. Min Act: -0.0002

Data Index: 484803 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0629. Min Act: -0.0002

Data Index: 152591 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0633. Min Act: -0.0002

Data Index: 852784 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0617. Min Act: -0.0002

Data Index: 583760 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0640. Min Act: -0.0002

Data Index: 419680 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0602. Min Act: -0.0002

Data Index: 132814 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1025341 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0632. Min Act: -0.0002

Data Index: 942081 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0627. Min Act: -0.0002

Data Index: 214054 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1009514 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0598. Min Act: -0.0002

Data Index: 299995 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0605. Min Act: -0.0002

Data Index: 859111 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0642. Min Act: -0.0002

Data Index: 10363 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0602. Min Act: -0.0002

Data Index: 163747 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0588. Min Act: -0.0002

Data Index: 81961 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0577. Min Act: -0.0002

Data Index: 493467 (C4 (Web Text))

Max Activating Token Index: 364