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

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

Neuron 40 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: 0.0789. Min Range: -0.0789

Max Act: 0.0770. Min Act: -0.0002

Data Index: 514889 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0789. Min Act: -0.0002

Data Index: 364028 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0763. Min Act: -0.0002

Data Index: 222458 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0762. Min Act: -0.0002

Data Index: 573439 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0746. Min Act: -0.0002

Data Index: 185728 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0621. Min Act: -0.0002

Data Index: 453400 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1047909 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0604. Min Act: -0.0002

Data Index: 305547 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0588. Min Act: -0.0002

Data Index: 120348 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1003189 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0581. Min Act: -0.0002

Data Index: 21316 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1047264 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0561. Min Act: -0.0002

Data Index: 919892 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1055828 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0600. Min Act: -0.0002

Data Index: 941688 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1211485 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1184640 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0559. Min Act: -0.0002

Data Index: 729777 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0562. Min Act: -0.0002

Data Index: 562900 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0549. Min Act: -0.0002

Data Index: 37764 (C4 (Web Text))

Max Activating Token Index: 234