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

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

Neuron 365 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.5035. Min Act: -0.0000

Data Index: 459695 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.4054. Min Act: -0.0000

Data Index: 817355 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.2717. Min Act: -0.0000

Data Index: 1050497 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.2112. Min Act: -0.0000

Data Index: 1259155 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1345871 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.1870. Min Act: -0.0000

Data Index: 786292 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.1463. Min Act: -0.0000

Data Index: 103804 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.0982. Min Act: -0.0000

Data Index: 627047 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.0855. Min Act: -0.0000

Data Index: 931815 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.0783. Min Act: -0.0000

Data Index: 459010 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.0779. Min Act: 0.0000

Data Index: 126835 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.0659. Min Act: -0.0000

Data Index: 409356 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.0442. Min Act: -0.0000

Data Index: 913007 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 1.5035. Min Range: -1.5035

Max Act: 0.9775. Min Act: -0.0000

Data Index: 307013 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1261994 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.0309. Min Act: -0.0000

Data Index: 743953 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 1.5035. Min Range: -1.5035

Max Act: 1.0220. Min Act: 0.0000

Data Index: 887979 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 1.5035. Min Range: -1.5035

Max Act: 0.9986. Min Act: -0.0000

Data Index: 467214 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 1.5035. Min Range: -1.5035

Max Act: 0.9858. Min Act: -0.0000

Data Index: 705506 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 1.5035. Min Range: -1.5035

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1004135 (C4 (Web Text))

Max Activating Token Index: 782