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

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

Neuron 1852 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8703. Min Act: -0.0000

Data Index: 1485837 (Python Code)

Max Activating Token Index: 363

Text #1

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.7858. Min Act: -0.0000

Data Index: 1433979 (Python Code)

Max Activating Token Index: 781

Text #2

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.6474. Min Act: -0.0000

Data Index: 1381932 (Python Code)

Max Activating Token Index: 735

Text #3

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.3991. Min Act: -0.0000

Data Index: 1542644 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1577706 (Python Code)

Max Activating Token Index: 321

Text #5

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.3949. Min Act: -0.0000

Data Index: 1557050 (Python Code)

Max Activating Token Index: 274

Text #6

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.3701. Min Act: -0.0000

Data Index: 1584084 (Python Code)

Max Activating Token Index: 584

Text #7

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.3184. Min Act: -0.0000

Data Index: 1407339 (Python Code)

Max Activating Token Index: 622

Text #8

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.3456. Min Act: -0.0000

Data Index: 1454678 (Python Code)

Max Activating Token Index: 722

Text #9

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1648341 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1469727 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.3539. Min Act: -0.0000

Data Index: 1591516 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1536373 (Python Code)

Max Activating Token Index: 467

Text #13

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.2541. Min Act: -0.0000

Data Index: 1492077 (Python Code)

Max Activating Token Index: 466

Text #14

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.1603. Min Act: -0.0000

Data Index: 1647082 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1486040 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1480659 (Python Code)

Max Activating Token Index: 228

Text #17

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1518532 (Python Code)

Max Activating Token Index: 216

Text #18

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.2014. Min Act: -0.0000

Data Index: 1604118 (Python Code)

Max Activating Token Index: 731

Text #19

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1478536 (Python Code)

Max Activating Token Index: 527