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

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

Neuron 2978 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0003

Data Index: 808334 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1205000 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0616. Min Act: -0.0003

Data Index: 652423 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0598. Min Act: -0.0003

Data Index: 91744 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0615. Min Act: -0.0003

Data Index: 195958 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0583. Min Act: -0.0003

Data Index: 197906 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0597. Min Act: -0.0003

Data Index: 793963 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0574. Min Act: -0.0003

Data Index: 476290 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0595. Min Act: -0.0003

Data Index: 921290 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0669. Min Act: -0.0003

Data Index: 676602 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1150240 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1334185 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1264565 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0582. Min Act: -0.0003

Data Index: 79583 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0551. Min Act: -0.0003

Data Index: 909011 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0508. Min Act: -0.0003

Data Index: 910656 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1026816 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0565. Min Act: -0.0003

Data Index: 666701 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1302233 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0563. Min Act: -0.0003

Data Index: 703682 (C4 (Web Text))

Max Activating Token Index: 202