Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 418 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1598079 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1413218 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1495467 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1534516 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1433184 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1399415 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1416123 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1584132 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1396857 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1634374 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0004

Data Index: 1511810 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1565071 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1618493 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1448987 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1454392 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1583689 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1387559 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1651594 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1512149 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1627928 (Python Code)

Max Activating Token Index: 24