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

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

Neuron 4365 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.3833. Min Act: -0.0001

Data Index: 1109426 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.3535. Min Act: -0.0001

Data Index: 86681 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.3042. Min Act: -0.0001

Data Index: 52922 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2876. Min Act: -0.0001

Data Index: 845477 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.3034. Min Act: -0.0001

Data Index: 105075 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2987. Min Act: -0.0001

Data Index: 74571 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2600. Min Act: -0.0001

Data Index: 272684 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2803. Min Act: -0.0001

Data Index: 1249273 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2862. Min Act: -0.0001

Data Index: 297657 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2880. Min Act: -0.0001

Data Index: 1359247 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2625. Min Act: -0.0001

Data Index: 761638 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1232564 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2446. Min Act: -0.0001

Data Index: 888185 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1091983 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2720. Min Act: -0.0001

Data Index: 1356746 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2229. Min Act: -0.0001

Data Index: 655389 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2451. Min Act: -0.0001

Data Index: 554878 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2328. Min Act: -0.0001

Data Index: 933914 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2587. Min Act: -0.0001

Data Index: 855168 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.3833. Min Range: -0.3833

Max Act: 0.2576. Min Act: -0.0001

Data Index: 395478 (C4 (Web Text))

Max Activating Token Index: 304