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

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

Neuron 4350 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1568. Min Range: -5.1568

Max Act: 5.1504. Min Act: -0.0000

Data Index: 942251 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 5.1568. Min Range: -5.1568

Max Act: 5.0323. Min Act: -0.0000

Data Index: 248037 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 5.1568. Min Range: -5.1568

Max Act: 5.0292. Min Act: -0.0000

Data Index: 768049 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 5.1568. Min Range: -5.1568

Max Act: 5.1568. Min Act: -0.0000

Data Index: 1136488 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 5.1568. Min Range: -5.1568

Max Act: 4.7721. Min Act: -0.0000

Data Index: 698789 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 5.1568. Min Range: -5.1568

Max Act: 4.3399. Min Act: -0.0000

Data Index: 76017 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 5.1568. Min Range: -5.1568

Max Act: 4.3255. Min Act: -0.0000

Data Index: 99231 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 5.1568. Min Range: -5.1568

Max Act: 4.2718. Min Act: -0.0000

Data Index: 144442 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 5.1568. Min Range: -5.1568

Max Act: 4.1482. Min Act: -0.0000

Data Index: 813330 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 5.1568. Min Range: -5.1568

Max Act: 4.0235. Min Act: -0.0000

Data Index: 951441 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.9528. Min Act: -0.0000

Data Index: 410727 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.6281. Min Act: -0.0000

Data Index: 1213843 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.5307. Min Act: -0.0000

Data Index: 442053 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.3794. Min Act: -0.0000

Data Index: 829912 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.5928. Min Act: -0.0000

Data Index: 570902 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.3194. Min Act: -0.0000

Data Index: 695866 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.1183. Min Act: -0.0000

Data Index: 1129503 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.2027. Min Act: -0.0000

Data Index: 738779 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.1493. Min Act: -0.0000

Data Index: 366129 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 5.1568. Min Range: -5.1568

Max Act: 3.1103. Min Act: -0.0000

Data Index: 1164208 (C4 (Web Text))

Max Activating Token Index: 658