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

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

Neuron 2325 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1561771 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1424633 (Python Code)

Max Activating Token Index: 1006

Text #2

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1478588 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1567392 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1429414 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1621174 (Python Code)

Max Activating Token Index: 909

Text #6

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1419633 (Python Code)

Max Activating Token Index: 285

Text #7

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1373223 (Python Code)

Max Activating Token Index: 748

Text #8

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1630333 (Python Code)

Max Activating Token Index: 953

Text #9

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1391057 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1588957 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1617468 (Python Code)

Max Activating Token Index: 417

Text #12

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1544205 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1399451 (Python Code)

Max Activating Token Index: 432

Text #14

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1585794 (Python Code)

Max Activating Token Index: 850

Text #15

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1391075 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1545510 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1471394 (Python Code)

Max Activating Token Index: 923

Text #18

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1401633 (Python Code)

Max Activating Token Index: 664

Text #19

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1417908 (Python Code)

Max Activating Token Index: 822