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

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

Neuron 2580 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2173. Min Act: -0.0000

Data Index: 210180 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2066. Min Act: -0.0000

Data Index: 221302 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1876. Min Act: -0.0000

Data Index: 868717 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2083. Min Act: -0.0000

Data Index: 911091 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1602957 (Python Code)

Max Activating Token Index: 835

Text #5

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1883. Min Act: -0.0000

Data Index: 153867 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1072473 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1813. Min Act: -0.0000

Data Index: 832836 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1745. Min Act: -0.0000

Data Index: 415189 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1508739 (Python Code)

Max Activating Token Index: 880

Text #10

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1815. Min Act: -0.0000

Data Index: 146894 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1313801 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1578382 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1759. Min Act: -0.0000

Data Index: 464468 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1582657 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1343322 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1933. Min Act: -0.0000

Data Index: 426320 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1919. Min Act: -0.0000

Data Index: 363578 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1619. Min Act: -0.0000

Data Index: 496134 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.2173. Min Range: -0.2173

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1389285 (Python Code)

Max Activating Token Index: 267