Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3232 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0686. Min Act: -0.0002

Data Index: 247794 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0663. Min Act: -0.0002

Data Index: 501615 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0614. Min Act: -0.0002

Data Index: 995196 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0636. Min Act: -0.0002

Data Index: 963168 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0627. Min Act: -0.0002

Data Index: 380606 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1001182 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0620. Min Act: -0.0002

Data Index: 221091 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0629. Min Act: -0.0002

Data Index: 88106 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1296104 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1565333 (Python Code)

Max Activating Token Index: 524

Text #10

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0595. Min Act: -0.0002

Data Index: 654428 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1620892 (Python Code)

Max Activating Token Index: 204

Text #12

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1083634 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1442466 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0579. Min Act: -0.0002

Data Index: 205153 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1324543 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0600. Min Act: -0.0002

Data Index: 187489 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0602. Min Act: -0.0002

Data Index: 222037 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1401569 (Python Code)

Max Activating Token Index: 408

Text #19

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0558. Min Act: -0.0002

Data Index: 297228 (C4 (Web Text))

Max Activating Token Index: 796