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

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

Neuron 1019 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.3311. Min Act: -0.0000

Data Index: 394475 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1505007 (Python Code)

Max Activating Token Index: 854

Text #2

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2613. Min Act: -0.0000

Data Index: 819076 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2778. Min Act: -0.0000

Data Index: 299544 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2102. Min Act: -0.0000

Data Index: 212143 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2099. Min Act: -0.0000

Data Index: 628898 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1608681 (Python Code)

Max Activating Token Index: 869

Text #7

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1385271 (Python Code)

Max Activating Token Index: 802

Text #8

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1742. Min Act: -0.0000

Data Index: 277917 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1815. Min Act: -0.0000

Data Index: 134796 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1673. Min Act: -0.0000

Data Index: 154737 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1452442 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1181411 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1796. Min Act: -0.0000

Data Index: 660326 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1211222 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1838. Min Act: -0.0000

Data Index: 800675 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1019311 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1823. Min Act: -0.0000

Data Index: 526845 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1661. Min Act: -0.0000

Data Index: 785084 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.1773. Min Act: -0.0000

Data Index: 26613 (C4 (Web Text))

Max Activating Token Index: 652