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

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

Neuron 31 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: 0.2209. Min Range: -0.2209

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1015108 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2032. Min Act: -0.0001

Data Index: 557024 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1887. Min Act: -0.0001

Data Index: 115960 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.2090. Min Act: -0.0000

Data Index: 384601 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1035856 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1733. Min Act: -0.0000

Data Index: 629630 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1891. Min Act: -0.0000

Data Index: 81324 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1707. Min Act: -0.0000

Data Index: 659535 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1345344 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1694. Min Act: -0.0000

Data Index: 181848 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1638. Min Act: -0.0000

Data Index: 454504 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1515. Min Act: -0.0000

Data Index: 695720 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1053428 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1821. Min Act: -0.0001

Data Index: 988852 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1560. Min Act: -0.0000

Data Index: 620613 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1801. Min Act: -0.0000

Data Index: 316865 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1729. Min Act: -0.0001

Data Index: 107631 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1150874 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1654. Min Act: -0.0000

Data Index: 306101 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.2209. Min Range: -0.2209

Max Act: 0.1458. Min Act: -0.0001

Data Index: 64359 (C4 (Web Text))

Max Activating Token Index: 158