Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3272 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0881. Min Act: -0.0002

Data Index: 552684 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0773. Min Act: -0.0002

Data Index: 782629 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0778. Min Act: -0.0002

Data Index: 493994 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0738. Min Act: -0.0002

Data Index: 696585 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0684. Min Act: -0.0002

Data Index: 204999 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1185746 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1235768 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0640. Min Act: -0.0002

Data Index: 21486 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0658. Min Act: -0.0002

Data Index: 951830 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0672. Min Act: -0.0002

Data Index: 304413 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1070346 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0630. Min Act: -0.0002

Data Index: 933249 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1339483 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0621. Min Act: -0.0002

Data Index: 572208 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0617. Min Act: -0.0002

Data Index: 273784 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1236387 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0641. Min Act: -0.0002

Data Index: 33659 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0582. Min Act: -0.0002

Data Index: 705601 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0619. Min Act: -0.0002

Data Index: 170367 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0588. Min Act: -0.0002

Data Index: 574496 (C4 (Web Text))

Max Activating Token Index: 97