Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 444 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0001

Data Index: 698496 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1087078 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0675. Min Act: -0.0001

Data Index: 904294 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0671. Min Act: -0.0001

Data Index: 533770 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1166179 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0625. Min Act: -0.0001

Data Index: 290951 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1228754 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1237020 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0576. Min Act: -0.0002

Data Index: 576199 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1008661 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0621. Min Act: -0.0001

Data Index: 426799 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0624. Min Act: -0.0001

Data Index: 517412 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0573. Min Act: -0.0002

Data Index: 983477 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0541. Min Act: -0.0002

Data Index: 946930 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0543. Min Act: -0.0002

Data Index: 759796 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0438. Min Act: -0.0001

Data Index: 968491 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0366. Min Act: -0.0001

Data Index: 601101 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0399. Min Act: -0.0001

Data Index: 23046 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1015143 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0383. Min Act: -0.0001

Data Index: 332895 (C4 (Web Text))

Max Activating Token Index: 44