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

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

Neuron 1233 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: 0.2903. Min Range: -0.2903

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1165081 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2159. Min Act: -0.0000

Data Index: 232098 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2141. Min Act: -0.0000

Data Index: 930429 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2154. Min Act: -0.0000

Data Index: 802432 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1971. Min Act: -0.0000

Data Index: 316268 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1127391 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1101932 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1887. Min Act: -0.0000

Data Index: 123776 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1966. Min Act: -0.0000

Data Index: 397488 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1741. Min Act: -0.0000

Data Index: 270925 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1785. Min Act: -0.0000

Data Index: 698277 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1333927 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1749. Min Act: -0.0000

Data Index: 916239 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1795. Min Act: -0.0000

Data Index: 511965 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1282131 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1003183 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1267048 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1721. Min Act: -0.0000

Data Index: 64144 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1779. Min Act: -0.0000

Data Index: 736911 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1058053 (C4 (Web Text))

Max Activating Token Index: 863