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

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

Neuron 2321 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.7551. Min Act: -0.0004

Data Index: 382238 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6765. Min Act: -0.0004

Data Index: 89547 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.7111. Min Act: -0.0004

Data Index: 526018 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6893. Min Act: -0.0004

Data Index: 33191 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6765. Min Act: -0.0004

Data Index: 678400 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6580. Min Act: -0.0004

Data Index: 572396 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6511. Min Act: -0.0004

Data Index: 390970 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6313. Min Act: -0.0004

Data Index: 421010 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5891. Min Act: -0.0004

Data Index: 910648 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5184. Min Act: -0.0004

Data Index: 320379 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6263. Min Act: -0.0004

Data Index: 1130492 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5934. Min Act: -0.0004

Data Index: 698561 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5216. Min Act: -0.0004

Data Index: 516730 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5361. Min Act: -0.0004

Data Index: 325465 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5900. Min Act: -0.0004

Data Index: 321237 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5709. Min Act: -0.0004

Data Index: 1049387 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5339. Min Act: -0.0004

Data Index: 1260341 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4981. Min Act: -0.0004

Data Index: 1348092 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5695. Min Act: -0.0004

Data Index: 102898 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5687. Min Act: -0.0004

Data Index: 746755 (C4 (Web Text))

Max Activating Token Index: 425