Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3189 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.6265. Min Act: -0.0003

Data Index: 1435876 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5757. Min Act: -0.0003

Data Index: 1370549 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5804. Min Act: -0.0003

Data Index: 1595238 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5560. Min Act: -0.0003

Data Index: 1366827 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5261. Min Act: -0.0003

Data Index: 1382484 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5188. Min Act: -0.0002

Data Index: 1609570 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5188. Min Act: -0.0003

Data Index: 1485521 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5026. Min Act: -0.0003

Data Index: 1523994 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5026. Min Act: -0.0003

Data Index: 1451856 (Python Code)

Max Activating Token Index: 29

Text #9

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5167. Min Act: -0.0003

Data Index: 1532122 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4979. Min Act: -0.0003

Data Index: 1431099 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4979. Min Act: -0.0003

Data Index: 1394240 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4891. Min Act: -0.0003

Data Index: 1441158 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4858. Min Act: -0.0003

Data Index: 1436618 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4851. Min Act: -0.0003

Data Index: 1614322 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4948. Min Act: -0.0002

Data Index: 1557077 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4922. Min Act: -0.0002

Data Index: 1418452 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4763. Min Act: -0.0003

Data Index: 1432953 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4763. Min Act: -0.0003

Data Index: 1651874 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4763. Min Act: -0.0002

Data Index: 1466425 (Python Code)

Max Activating Token Index: 14