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

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

Neuron 46 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1716. Min Act: -0.0001

Data Index: 328466 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1899. Min Act: -0.0001

Data Index: 438241 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1799. Min Act: -0.0000

Data Index: 474054 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1739. Min Act: -0.0001

Data Index: 452861 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1743. Min Act: -0.0001

Data Index: 794834 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1551. Min Act: -0.0001

Data Index: 129274 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1419. Min Act: -0.0001

Data Index: 56205 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1302. Min Act: -0.0001

Data Index: 679146 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0945. Min Act: -0.0001

Data Index: 483365 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0874. Min Act: -0.0001

Data Index: 1167259 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1242. Min Act: -0.0001

Data Index: 769896 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0830. Min Act: -0.0001

Data Index: 309534 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0758. Min Act: -0.0000

Data Index: 287409 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0950. Min Act: -0.0001

Data Index: 871846 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0709. Min Act: -0.0001

Data Index: 908876 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0604. Min Act: -0.0001

Data Index: 720613 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0837. Min Act: -0.0001

Data Index: 1312545 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1145. Min Act: -0.0000

Data Index: 717256 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0587. Min Act: -0.0001

Data Index: 81463 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0187. Min Act: -0.0001

Data Index: 35151 (C4 (Web Text))

Max Activating Token Index: 116