Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1892 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1539952 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1625698 (Python Code)

Max Activating Token Index: 997

Text #2

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1638121 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1376932 (Python Code)

Max Activating Token Index: 672

Text #4

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1624305 (Python Code)

Max Activating Token Index: 529

Text #5

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1554822 (Python Code)

Max Activating Token Index: 819

Text #6

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1568502 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1627163 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1577906 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1654712 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1622579 (Python Code)

Max Activating Token Index: 466

Text #11

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1441470 (Python Code)

Max Activating Token Index: 736

Text #12

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1580273 (Python Code)

Max Activating Token Index: 137

Text #13

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1467422 (Python Code)

Max Activating Token Index: 195

Text #14

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1423579 (Python Code)

Max Activating Token Index: 544

Text #15

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1570780 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1421542 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1469867 (Python Code)

Max Activating Token Index: 807

Text #18

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1457719 (Python Code)

Max Activating Token Index: 858

Text #19

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1511155 (Python Code)

Max Activating Token Index: 636