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

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

Neuron 2096 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.3927. Min Act: 0.0001

Data Index: 1380714 (Python Code)

Max Activating Token Index: 70

Text #1

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.3585. Min Act: 0.0000

Data Index: 1641081 (Python Code)

Max Activating Token Index: 474

Text #2

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.2558. Min Act: 0.0001

Data Index: 1425426 (Python Code)

Max Activating Token Index: 308

Text #3

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1375434 (Python Code)

Max Activating Token Index: 324

Text #4

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.2031. Min Act: 0.0001

Data Index: 1568437 (Python Code)

Max Activating Token Index: 428

Text #5

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1433088 (Python Code)

Max Activating Token Index: 929

Text #6

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.2009. Min Act: 0.0001

Data Index: 1549896 (Python Code)

Max Activating Token Index: 460

Text #7

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1420932 (Python Code)

Max Activating Token Index: 734

Text #8

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1652031 (Python Code)

Max Activating Token Index: 824

Text #9

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1469451 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0936. Min Act: -0.0000

Data Index: 1574342 (Python Code)

Max Activating Token Index: 780

Text #11

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1539892 (Python Code)

Max Activating Token Index: 859

Text #12

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1476402 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1653698 (Python Code)

Max Activating Token Index: 541

Text #14

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0376. Min Act: -0.0000

Data Index: 1415502 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1508583 (Python Code)

Max Activating Token Index: 996

Text #16

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0200. Min Act: -0.0000

Data Index: 1483938 (Python Code)

Max Activating Token Index: 535

Text #17

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0160. Min Act: 0.0001

Data Index: 1529368 (Python Code)

Max Activating Token Index: 125

Text #18

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1517556 (Python Code)

Max Activating Token Index: 736

Text #19

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0551. Min Act: 0.0001

Data Index: 1474583 (Python Code)

Max Activating Token Index: 732