Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3221 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.3075. Min Act: -0.0001

Data Index: 303380 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.1957. Min Act: -0.0001

Data Index: 1452243 (Python Code)

Max Activating Token Index: 974

Text #2

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.2072. Min Act: -0.0001

Data Index: 245398 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.1355. Min Act: -0.0001

Data Index: 931580 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0497. Min Act: -0.0001

Data Index: 1154859 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0357. Min Act: -0.0001

Data Index: 1295717 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.1883. Min Act: -0.0001

Data Index: 505267 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.1665. Min Act: -0.0001

Data Index: 226627 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.1413. Min Act: -0.0001

Data Index: 740221 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0378. Min Act: -0.0001

Data Index: 279968 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.1117. Min Act: -0.0001

Data Index: 623862 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9732. Min Act: -0.0001

Data Index: 342629 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9945. Min Act: -0.0001

Data Index: 895038 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0236. Min Act: -0.0001

Data Index: 425108 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0399. Min Act: -0.0001

Data Index: 130275 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0439. Min Act: -0.0001

Data Index: 177679 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0713. Min Act: -0.0001

Data Index: 456600 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0340. Min Act: -0.0001

Data Index: 254374 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.3075. Min Range: -1.3075

Max Act: 0.9757. Min Act: -0.0001

Data Index: 636817 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 1.3075. Min Range: -1.3075

Max Act: 1.0627. Min Act: -0.0001

Data Index: 1139700 (C4 (Web Text))

Max Activating Token Index: 983