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

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

Neuron 3501 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2660. Min Act: -0.0002

Data Index: 1370931 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2443. Min Act: -0.0002

Data Index: 1373687 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2385. Min Act: -0.0002

Data Index: 1650279 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2201. Min Act: -0.0002

Data Index: 615743 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2189. Min Act: -0.0002

Data Index: 1387682 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2139. Min Act: -0.0002

Data Index: 1425403 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1516899 (Python Code)

Max Activating Token Index: 552

Text #7

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2113. Min Act: -0.0002

Data Index: 1655145 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2048. Min Act: -0.0002

Data Index: 1485660 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2031. Min Act: -0.0002

Data Index: 1573154 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2020. Min Act: -0.0002

Data Index: 1451431 (Python Code)

Max Activating Token Index: 72

Text #11

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2012. Min Act: -0.0002

Data Index: 1424279 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2011. Min Act: -0.0002

Data Index: 1624107 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1985. Min Act: -0.0002

Data Index: 1595668 (Python Code)

Max Activating Token Index: 45

Text #14

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1971. Min Act: -0.0002

Data Index: 1523024 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1970. Min Act: -0.0002

Data Index: 1426154 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1965. Min Act: -0.0002

Data Index: 1516045 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1944. Min Act: -0.0002

Data Index: 1581605 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1934. Min Act: -0.0002

Data Index: 1614220 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1926. Min Act: -0.0002

Data Index: 1604274 (Python Code)

Max Activating Token Index: 189