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

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

Neuron 2562 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: 1.9124. Min Range: -1.9124

Max Act: 1.9124. Min Act: -0.0000

Data Index: 1570025 (Python Code)

Max Activating Token Index: 439

Text #1

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.8809. Min Act: -0.0000

Data Index: 1539032 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.8050. Min Act: -0.0000

Data Index: 1426737 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.7551. Min Act: -0.0000

Data Index: 1423382 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6779. Min Act: -0.0000

Data Index: 1471270 (Python Code)

Max Activating Token Index: 455

Text #5

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6757. Min Act: -0.0000

Data Index: 1575019 (Python Code)

Max Activating Token Index: 936

Text #6

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6469. Min Act: -0.0000

Data Index: 1528724 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6428. Min Act: -0.0000

Data Index: 1559180 (Python Code)

Max Activating Token Index: 566

Text #8

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6272. Min Act: -0.0000

Data Index: 1369184 (Python Code)

Max Activating Token Index: 754

Text #9

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6272. Min Act: -0.0000

Data Index: 1526797 (Python Code)

Max Activating Token Index: 952

Text #10

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6242. Min Act: -0.0000

Data Index: 1596798 (Python Code)

Max Activating Token Index: 528

Text #11

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6190. Min Act: -0.0000

Data Index: 1483596 (Python Code)

Max Activating Token Index: 944

Text #12

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1557701 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.6708. Min Act: -0.0000

Data Index: 1519902 (Python Code)

Max Activating Token Index: 294

Text #14

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.4691. Min Act: -0.0000

Data Index: 1579458 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5604. Min Act: -0.0000

Data Index: 1490875 (Python Code)

Max Activating Token Index: 601

Text #16

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5492. Min Act: -0.0000

Data Index: 1446213 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1398861 (Python Code)

Max Activating Token Index: 939

Text #18

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5434. Min Act: -0.0000

Data Index: 1627276 (Python Code)

Max Activating Token Index: 555

Text #19

Max Range: 1.9124. Min Range: -1.9124

Max Act: 1.5384. Min Act: -0.0000

Data Index: 1374560 (Python Code)

Max Activating Token Index: 258