Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1824 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1085915 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1106968 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2221. Min Act: -0.0000

Data Index: 468525 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2138. Min Act: -0.0000

Data Index: 330063 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2149. Min Act: -0.0001

Data Index: 841752 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2125. Min Act: -0.0001

Data Index: 81678 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1950. Min Act: -0.0000

Data Index: 970961 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1946. Min Act: -0.0000

Data Index: 749843 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1921. Min Act: -0.0001

Data Index: 246522 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1137156 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1862. Min Act: -0.0000

Data Index: 217899 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1831. Min Act: -0.0000

Data Index: 113076 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1040552 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1281485 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1632. Min Act: -0.0000

Data Index: 739771 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1026762 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1633. Min Act: -0.0001

Data Index: 933747 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1749. Min Act: -0.0000

Data Index: 706028 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1004330 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1069467 (C4 (Web Text))

Max Activating Token Index: 494