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

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

Neuron 4864 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: 0.0649. Min Range: -0.0649

Max Act: 0.0581. Min Act: -0.0002

Data Index: 301009 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1014178 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1199461 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0582. Min Act: -0.0002

Data Index: 830864 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0617. Min Act: -0.0002

Data Index: 811378 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0639. Min Act: -0.0002

Data Index: 181210 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0595. Min Act: -0.0002

Data Index: 295381 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0615. Min Act: -0.0002

Data Index: 254968 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0630. Min Act: -0.0002

Data Index: 728121 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0633. Min Act: -0.0002

Data Index: 580267 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0002

Data Index: 480170 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1253678 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0623. Min Act: -0.0002

Data Index: 343440 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0617. Min Act: -0.0002

Data Index: 908965 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0586. Min Act: -0.0002

Data Index: 292265 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0588. Min Act: -0.0002

Data Index: 94808 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0587. Min Act: -0.0002

Data Index: 117231 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0539. Min Act: -0.0002

Data Index: 880262 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0534. Min Act: -0.0002

Data Index: 660400 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1172294 (C4 (Web Text))

Max Activating Token Index: 649