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

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

Neuron 631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.2038. Min Act: -0.0002

Data Index: 343680 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1765. Min Act: -0.0002

Data Index: 480614 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1739. Min Act: -0.0002

Data Index: 171945 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1623. Min Act: -0.0002

Data Index: 1016067 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1571. Min Act: -0.0002

Data Index: 1314241 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1540. Min Act: -0.0002

Data Index: 1065399 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1514. Min Act: -0.0002

Data Index: 377794 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1562. Min Act: -0.0002

Data Index: 1042659 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1483. Min Act: -0.0002

Data Index: 794428 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1480. Min Act: -0.0002

Data Index: 1068158 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1328780 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1459. Min Act: -0.0002

Data Index: 746573 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1017995 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1304. Min Act: -0.0002

Data Index: 526196 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1392. Min Act: -0.0002

Data Index: 727812 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1264. Min Act: -0.0002

Data Index: 211022 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1322. Min Act: -0.0002

Data Index: 287568 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1294. Min Act: -0.0002

Data Index: 971600 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1284. Min Act: -0.0002

Data Index: 244177 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1307. Min Act: -0.0002

Data Index: 826337 (C4 (Web Text))

Max Activating Token Index: 951