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

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

Neuron 350 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: 0.9909. Min Range: -0.9909

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1622326 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1405519 (Python Code)

Max Activating Token Index: 490

Text #2

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1416287 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1592289 (Python Code)

Max Activating Token Index: 975

Text #4

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1628530 (Python Code)

Max Activating Token Index: 753

Text #5

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1382692 (Python Code)

Max Activating Token Index: 1018

Text #6

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1452552 (Python Code)

Max Activating Token Index: 851

Text #7

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1459902 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1649660 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1548928 (Python Code)

Max Activating Token Index: 241

Text #10

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1381511 (Python Code)

Max Activating Token Index: 964

Text #11

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1462139 (Python Code)

Max Activating Token Index: 46

Text #12

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1441088 (Python Code)

Max Activating Token Index: 837

Text #13

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1386311 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1522047 (Python Code)

Max Activating Token Index: 131

Text #15

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1550637 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1522925 (Python Code)

Max Activating Token Index: 1004

Text #17

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1433629 (Python Code)

Max Activating Token Index: 57

Text #18

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1583833 (Python Code)

Max Activating Token Index: 496

Text #19

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1412042 (Python Code)

Max Activating Token Index: 627