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

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

Neuron 5010 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0920. Min Range: -2.0920

Max Act: 2.0920. Min Act: -0.0000

Data Index: 777198 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.9278. Min Act: -0.0000

Data Index: 1169056 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 2.0920. Min Range: -2.0920

Max Act: 2.0478. Min Act: -0.0000

Data Index: 9015 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.8954. Min Act: -0.0000

Data Index: 443802 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.8213. Min Act: -0.0000

Data Index: 445202 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.8063. Min Act: -0.0000

Data Index: 682663 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.6863. Min Act: -0.0000

Data Index: 508476 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.7688. Min Act: -0.0000

Data Index: 567001 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.7638. Min Act: -0.0000

Data Index: 930623 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.6633. Min Act: -0.0000

Data Index: 356503 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.5047. Min Act: -0.0000

Data Index: 1228805 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.6475. Min Act: -0.0000

Data Index: 402121 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.5010. Min Act: -0.0000

Data Index: 510697 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.5604. Min Act: -0.0000

Data Index: 1315125 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.5573. Min Act: -0.0000

Data Index: 868204 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.5392. Min Act: -0.0000

Data Index: 367698 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.5173. Min Act: -0.0000

Data Index: 58856 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.4192. Min Act: -0.0000

Data Index: 206783 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.4075. Min Act: -0.0000

Data Index: 274864 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 2.0920. Min Range: -2.0920

Max Act: 1.4808. Min Act: -0.0000

Data Index: 162217 (C4 (Web Text))

Max Activating Token Index: 122