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

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

Neuron 5385 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.3075. Min Act: -0.0000

Data Index: 754888 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1037527 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1172359 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2695. Min Act: -0.0000

Data Index: 692538 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1072761 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1226254 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2374. Min Act: -0.0000

Data Index: 741231 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2266. Min Act: -0.0000

Data Index: 440595 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2156. Min Act: -0.0000

Data Index: 54048 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.1928. Min Act: -0.0000

Data Index: 954501 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2176. Min Act: -0.0000

Data Index: 512764 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2203. Min Act: -0.0000

Data Index: 927260 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2118. Min Act: -0.0000

Data Index: 36586 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2138. Min Act: -0.0000

Data Index: 208664 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.1972. Min Act: -0.0000

Data Index: 208239 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1322968 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.1919. Min Act: -0.0000

Data Index: 290430 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1183316 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.1821. Min Act: -0.0000

Data Index: 616642 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.1633. Min Act: -0.0000

Data Index: 924893 (C4 (Web Text))

Max Activating Token Index: 327