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

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

Neuron 1280 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.4076. Min Act: -0.0000

Data Index: 484803 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.5196. Min Act: -0.0000

Data Index: 726405 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.1348. Min Act: -0.0000

Data Index: 439241 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.1756. Min Act: -0.0000

Data Index: 760385 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1090126 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8600. Min Act: -0.0000

Data Index: 231981 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9254. Min Act: -0.0000

Data Index: 301190 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8870. Min Act: -0.0000

Data Index: 977584 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1572803 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1616188 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1156806 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1518322 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1430231 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1594550 (Python Code)

Max Activating Token Index: 893

Text #14

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1522321 (Python Code)

Max Activating Token Index: 71

Text #15

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1290475 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7876. Min Act: -0.0000

Data Index: 83266 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7710. Min Act: -0.0000

Data Index: 549504 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1576833 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1554608 (Python Code)

Max Activating Token Index: 923