Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1620 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2389. Min Act: -0.0002

Data Index: 1049459 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2157. Min Act: -0.0002

Data Index: 1183371 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2223. Min Act: -0.0001

Data Index: 148005 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2023. Min Act: -0.0001

Data Index: 673618 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2012. Min Act: -0.0002

Data Index: 1241761 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2010. Min Act: -0.0002

Data Index: 1040288 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2054. Min Act: -0.0001

Data Index: 145187 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2045. Min Act: -0.0001

Data Index: 552976 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1958. Min Act: 0.0000

Data Index: 591008 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1991. Min Act: -0.0001

Data Index: 327726 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1867. Min Act: -0.0002

Data Index: 111017 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2021. Min Act: -0.0002

Data Index: 1314767 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1304661 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2008. Min Act: -0.0002

Data Index: 905802 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1914. Min Act: -0.0001

Data Index: 497745 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1898. Min Act: -0.0001

Data Index: 133012 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1870. Min Act: -0.0002

Data Index: 560298 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1804. Min Act: -0.0001

Data Index: 712619 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1858. Min Act: -0.0002

Data Index: 736772 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1790. Min Act: -0.0002

Data Index: 924470 (C4 (Web Text))

Max Activating Token Index: 950