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

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

Neuron 2434 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.8533. Min Act: -0.0000

Data Index: 1378886 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.9290. Min Act: -0.0000

Data Index: 1497370 (Python Code)

Max Activating Token Index: 244

Text #2

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.6249. Min Act: -0.0000

Data Index: 1574446 (Python Code)

Max Activating Token Index: 604

Text #3

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.8119. Min Act: -0.0000

Data Index: 1642298 (Python Code)

Max Activating Token Index: 413

Text #4

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.7702. Min Act: -0.0000

Data Index: 1625713 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.7222. Min Act: -0.0000

Data Index: 1485992 (Python Code)

Max Activating Token Index: 869

Text #6

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.5321. Min Act: -0.0000

Data Index: 1589760 (Python Code)

Max Activating Token Index: 651

Text #7

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.5229. Min Act: -0.0000

Data Index: 1385119 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.4620. Min Act: -0.0000

Data Index: 1490122 (Python Code)

Max Activating Token Index: 822

Text #9

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.8829. Min Act: -0.0000

Data Index: 1560509 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.5570. Min Act: -0.0000

Data Index: 1457889 (Python Code)

Max Activating Token Index: 598

Text #11

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.4996. Min Act: -0.0000

Data Index: 1369416 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.4902. Min Act: -0.0000

Data Index: 1566394 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.4618. Min Act: -0.0000

Data Index: 1623771 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.4603. Min Act: -0.0000

Data Index: 1615963 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.4456. Min Act: -0.0000

Data Index: 1418354 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.3051. Min Act: -0.0000

Data Index: 1587952 (Python Code)

Max Activating Token Index: 592

Text #17

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.6726. Min Act: -0.0000

Data Index: 1374829 (Python Code)

Max Activating Token Index: 999

Text #18

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.3917. Min Act: -0.0000

Data Index: 1477548 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.3793. Min Act: -0.0000

Data Index: 1510496 (Python Code)

Max Activating Token Index: 513