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

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

Neuron 1976 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.8397. Min Act: -0.0000

Data Index: 539238 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.8252. Min Act: -0.0000

Data Index: 172567 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.5466. Min Act: -0.0000

Data Index: 837328 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.6062. Min Act: -0.0000

Data Index: 508677 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.5433. Min Act: -0.0000

Data Index: 809136 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.5718. Min Act: -0.0000

Data Index: 587618 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.4305. Min Act: -0.0000

Data Index: 1317666 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.1977. Min Act: -0.0000

Data Index: 1108103 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.4358. Min Act: -0.0000

Data Index: 1039915 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.1626. Min Act: -0.0000

Data Index: 585240 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.2482. Min Act: -0.0000

Data Index: 261982 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.2143. Min Act: -0.0000

Data Index: 1252994 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.2530. Min Act: -0.0000

Data Index: 511844 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.0100. Min Act: -0.0000

Data Index: 184694 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.0799. Min Act: -0.0000

Data Index: 1106478 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.1991. Min Act: -0.0000

Data Index: 112753 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.0692. Min Act: -0.0000

Data Index: 984200 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 3.8397. Min Range: -3.8397

Max Act: 1.9414. Min Act: -0.0000

Data Index: 874817 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 3.8397. Min Range: -3.8397

Max Act: 1.9466. Min Act: -0.0000

Data Index: 139876 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 3.8397. Min Range: -3.8397

Max Act: 2.0497. Min Act: -0.0000

Data Index: 901443 (C4 (Web Text))

Max Activating Token Index: 474