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

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

Neuron 1398 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: 0.2812. Min Range: -0.2812

Max Act: 0.2812. Min Act: -0.0000

Data Index: 434458 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2365. Min Act: -0.0000

Data Index: 820498 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2118. Min Act: -0.0000

Data Index: 95213 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.2069. Min Act: -0.0000

Data Index: 532223 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1926. Min Act: -0.0000

Data Index: 561846 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1243218 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1829. Min Act: -0.0000

Data Index: 538978 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1752. Min Act: 0.0000

Data Index: 759107 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1576170 (Python Code)

Max Activating Token Index: 651

Text #9

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1848. Min Act: -0.0000

Data Index: 548692 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1645. Min Act: -0.0000

Data Index: 947217 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1662. Min Act: -0.0000

Data Index: 584801 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1672. Min Act: -0.0000

Data Index: 694770 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1453835 (Python Code)

Max Activating Token Index: 454

Text #14

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1678. Min Act: -0.0000

Data Index: 817178 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1218378 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1190106 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1629. Min Act: 0.0000

Data Index: 1253369 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1614. Min Act: -0.0000

Data Index: 154496 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.2812. Min Range: -0.2812

Max Act: 0.1657. Min Act: -0.0000

Data Index: 226404 (C4 (Web Text))

Max Activating Token Index: 376