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

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

Neuron 9 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.2526. Min Act: -0.0000

Data Index: 904796 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1352849 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1847. Min Act: -0.0000

Data Index: 483050 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1870. Min Act: -0.0000

Data Index: 874185 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1028417 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1837. Min Act: -0.0000

Data Index: 431394 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1261359 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1574. Min Act: -0.0000

Data Index: 260651 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1084391 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1860. Min Act: -0.0000

Data Index: 493937 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1858. Min Act: -0.0000

Data Index: 82697 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1701. Min Act: -0.0000

Data Index: 328837 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1698. Min Act: -0.0000

Data Index: 395221 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1640. Min Act: -0.0000

Data Index: 110729 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1627. Min Act: -0.0000

Data Index: 580348 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1665. Min Act: -0.0000

Data Index: 322308 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1649. Min Act: -0.0000

Data Index: 311859 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1246732 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1596. Min Act: -0.0000

Data Index: 301383 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.2526. Min Range: -0.2526

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1003451 (C4 (Web Text))

Max Activating Token Index: 326