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

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

Neuron 4904 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: 0.5589. Min Range: -0.5589

Max Act: 0.5589. Min Act: -0.0000

Data Index: 312541 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4433. Min Act: -0.0000

Data Index: 285475 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4569. Min Act: -0.0000

Data Index: 98837 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4486. Min Act: -0.0000

Data Index: 289980 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1323928 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4328. Min Act: -0.0000

Data Index: 491600 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1276550 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3837. Min Act: -0.0000

Data Index: 720287 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3716. Min Act: -0.0000

Data Index: 959110 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4032. Min Act: -0.0000

Data Index: 14984 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1252407 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3827. Min Act: -0.0000

Data Index: 814047 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1255257 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3739. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3349. Min Act: -0.0000

Data Index: 863571 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1005115 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3672. Min Act: -0.0000

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3483. Min Act: -0.0000

Data Index: 837030 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1228956 (C4 (Web Text))

Max Activating Token Index: 834