Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 477 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2668. Min Act: -0.0000

Data Index: 666458 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2523. Min Act: -0.0000

Data Index: 12551 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2268. Min Act: -0.0000

Data Index: 654670 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1323695 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1948. Min Act: -0.0000

Data Index: 362015 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1883. Min Act: -0.0000

Data Index: 975483 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1698. Min Act: -0.0000

Data Index: 18040 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1844. Min Act: -0.0000

Data Index: 295316 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1822. Min Act: -0.0000

Data Index: 763624 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1854. Min Act: -0.0000

Data Index: 896442 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1720. Min Act: -0.0000

Data Index: 386529 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1716. Min Act: -0.0000

Data Index: 536480 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1678. Min Act: -0.0000

Data Index: 644188 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1736. Min Act: -0.0000

Data Index: 11330 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1840. Min Act: -0.0000

Data Index: 290716 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1067870 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1014046 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1005787 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1095451 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.2668. Min Range: -0.2668

Max Act: 0.1680. Min Act: -0.0000

Data Index: 685235 (C4 (Web Text))

Max Activating Token Index: 712