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

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

Neuron 2628 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: 0.0999. Min Range: -0.0999

Max Act: 0.0872. Min Act: -0.0002

Data Index: 670937 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1118538 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0884. Min Act: -0.0002

Data Index: 10264 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0860. Min Act: -0.0002

Data Index: 646607 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1016300 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0799. Min Act: -0.0002

Data Index: 68342 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1242263 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0806. Min Act: -0.0002

Data Index: 617034 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0772. Min Act: -0.0002

Data Index: 365097 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0830. Min Act: -0.0002

Data Index: 190784 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0768. Min Act: -0.0002

Data Index: 563955 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0823. Min Act: -0.0002

Data Index: 119284 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0688. Min Act: -0.0002

Data Index: 51923 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0770. Min Act: -0.0002

Data Index: 520470 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0755. Min Act: -0.0002

Data Index: 92365 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0795. Min Act: -0.0002

Data Index: 913289 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0791. Min Act: -0.0002

Data Index: 747946 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1250871 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0794. Min Act: -0.0002

Data Index: 304795 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0791. Min Act: -0.0002

Data Index: 279552 (C4 (Web Text))

Max Activating Token Index: 16