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

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

Neuron 160 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.2388. Min Act: -0.0000

Data Index: 875855 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.2391. Min Act: -0.0000

Data Index: 658399 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.0986. Min Act: -0.0000

Data Index: 165629 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.0902. Min Act: -0.0000

Data Index: 597422 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1042164 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9753. Min Act: -0.0000

Data Index: 610304 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1330738 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9788. Min Act: -0.0000

Data Index: 23129 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9534. Min Act: -0.0000

Data Index: 952097 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9438. Min Act: -0.0000

Data Index: 178624 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9111. Min Act: -0.0000

Data Index: 426967 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9785. Min Act: -0.0000

Data Index: 650406 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9804. Min Act: -0.0000

Data Index: 151106 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1337401 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9535. Min Act: -0.0000

Data Index: 468573 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8823. Min Act: -0.0000

Data Index: 402653 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8446. Min Act: -0.0000

Data Index: 139337 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8476. Min Act: -0.0000

Data Index: 369142 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8360. Min Act: -0.0000

Data Index: 433341 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8818. Min Act: -0.0000

Data Index: 756314 (C4 (Web Text))

Max Activating Token Index: 260