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

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

Neuron 4880 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: 0.0773. Min Range: -0.0773

Max Act: 0.0773. Min Act: -0.0002

Data Index: 961117 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0669. Min Act: -0.0002

Data Index: 301936 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0618. Min Act: -0.0002

Data Index: 808504 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0684. Min Act: -0.0002

Data Index: 68468 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0687. Min Act: -0.0002

Data Index: 422550 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0596. Min Act: -0.0002

Data Index: 559698 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1213124 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0614. Min Act: -0.0002

Data Index: 589522 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0636. Min Act: -0.0002

Data Index: 811217 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1043554 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0636. Min Act: -0.0002

Data Index: 226999 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0639. Min Act: -0.0002

Data Index: 779119 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1308622 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0604. Min Act: -0.0002

Data Index: 21421 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0621. Min Act: -0.0002

Data Index: 318567 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0543. Min Act: -0.0002

Data Index: 150585 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0609. Min Act: -0.0002

Data Index: 256104 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0570. Min Act: -0.0002

Data Index: 40387 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0544. Min Act: -0.0002

Data Index: 875059 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0593. Min Act: -0.0002

Data Index: 707885 (C4 (Web Text))

Max Activating Token Index: 344