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

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

Neuron 3524 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: 0.2371. Min Range: -0.2371

Max Act: 0.2371. Min Act: -0.0002

Data Index: 675352 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2234. Min Act: -0.0002

Data Index: 316330 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1818. Min Act: -0.0002

Data Index: 1355613 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1787. Min Act: -0.0002

Data Index: 168752 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1828. Min Act: -0.0002

Data Index: 1207065 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1767. Min Act: -0.0002

Data Index: 487819 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1617. Min Act: -0.0002

Data Index: 1244360 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1620. Min Act: -0.0002

Data Index: 702210 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1500. Min Act: -0.0002

Data Index: 104381 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1531. Min Act: -0.0002

Data Index: 504786 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1566. Min Act: -0.0002

Data Index: 46944 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1521. Min Act: -0.0002

Data Index: 296966 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1420. Min Act: -0.0002

Data Index: 729354 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1510. Min Act: -0.0002

Data Index: 283205 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1443. Min Act: -0.0002

Data Index: 133818 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1472. Min Act: -0.0002

Data Index: 622793 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1425. Min Act: -0.0002

Data Index: 688362 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1422. Min Act: -0.0002

Data Index: 924114 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1412. Min Act: -0.0002

Data Index: 972055 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1358. Min Act: -0.0002

Data Index: 692806 (C4 (Web Text))

Max Activating Token Index: 59