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

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

Neuron 2208 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0002

Data Index: 893267 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1294764 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0002

Data Index: 171347 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0430. Min Act: -0.0002

Data Index: 985155 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0447. Min Act: -0.0002

Data Index: 795169 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0367. Min Act: -0.0002

Data Index: 43031 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0387. Min Act: -0.0002

Data Index: 565942 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1335202 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0378. Min Act: -0.0002

Data Index: 216982 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0432. Min Act: -0.0002

Data Index: 150018 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1174469 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0358. Min Act: -0.0002

Data Index: 618400 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1041387 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0399. Min Act: -0.0002

Data Index: 926883 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0400. Min Act: -0.0002

Data Index: 979816 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0352. Min Act: -0.0002

Data Index: 671040 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0364. Min Act: -0.0002

Data Index: 781905 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0360. Min Act: -0.0002

Data Index: 368324 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1124148 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0370. Min Act: -0.0002

Data Index: 254443 (C4 (Web Text))

Max Activating Token Index: 61