Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1646 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.6930. Min Act: -0.0000

Data Index: 933067 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.4394. Min Act: -0.0000

Data Index: 884106 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.4341. Min Act: -0.0000

Data Index: 1065207 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.3887. Min Act: -0.0000

Data Index: 564561 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.4523. Min Act: -0.0000

Data Index: 621650 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.3288. Min Act: -0.0000

Data Index: 166147 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.3046. Min Act: -0.0000

Data Index: 303701 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.3891. Min Act: -0.0000

Data Index: 406208 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.3771. Min Act: -0.0000

Data Index: 958538 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.3811. Min Act: -0.0000

Data Index: 635697 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.2978. Min Act: -0.0000

Data Index: 403345 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.2852. Min Act: -0.0000

Data Index: 402226 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1026790 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.3066. Min Act: -0.0000

Data Index: 739656 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.2500. Min Act: -0.0000

Data Index: 975281 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1047601 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.2113. Min Act: -0.0000

Data Index: 778582 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.2037. Min Act: -0.0000

Data Index: 419653 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.1994. Min Act: -0.0000

Data Index: 463240 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 1.6930. Min Range: -1.6930

Max Act: 1.1837. Min Act: -0.0000

Data Index: 831452 (C4 (Web Text))

Max Activating Token Index: 526