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

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

Neuron 3491 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: 1.0589. Min Range: -1.0589

Max Act: 1.0589. Min Act: -0.0000

Data Index: 272985 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9212. Min Act: 0.0000

Data Index: 737857 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8176. Min Act: -0.0000

Data Index: 268333 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1082079 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7696. Min Act: -0.0000

Data Index: 872456 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8083. Min Act: -0.0000

Data Index: 783153 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8320. Min Act: -0.0000

Data Index: 337983 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7799. Min Act: -0.0000

Data Index: 815537 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7904. Min Act: -0.0000

Data Index: 815874 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7773. Min Act: -0.0000

Data Index: 358726 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1347761 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7517. Min Act: -0.0000

Data Index: 943148 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7673. Min Act: -0.0000

Data Index: 162903 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7234. Min Act: -0.0000

Data Index: 550647 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7766. Min Act: -0.0000

Data Index: 127310 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7195. Min Act: -0.0000

Data Index: 958639 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1501415 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7085. Min Act: -0.0000

Data Index: 887673 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7731. Min Act: -0.0000

Data Index: 918279 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1177060 (C4 (Web Text))

Max Activating Token Index: 583