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

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

Neuron 3062 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: 0.6655. Min Range: -0.6655

Max Act: 0.6655. Min Act: -0.0000

Data Index: 780797 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6237. Min Act: -0.0000

Data Index: 821876 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5894. Min Act: -0.0000

Data Index: 254146 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1261595 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5246. Min Act: -0.0000

Data Index: 347770 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5227. Min Act: -0.0000

Data Index: 151586 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5096. Min Act: -0.0000

Data Index: 141316 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1092940 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4408. Min Act: -0.0000

Data Index: 451437 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4768. Min Act: -0.0000

Data Index: 456508 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4509. Min Act: -0.0000

Data Index: 5570 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4243. Min Act: -0.0000

Data Index: 20349 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4018. Min Act: -0.0000

Data Index: 493301 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4307. Min Act: -0.0000

Data Index: 194891 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1307268 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1182724 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4071. Min Act: -0.0000

Data Index: 20458 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1074703 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.3990. Min Act: -0.0000

Data Index: 426921 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4139. Min Act: -0.0000

Data Index: 486499 (C4 (Web Text))

Max Activating Token Index: 275