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

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

Neuron 1373 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.6877. Min Act: -0.0000

Data Index: 1126923 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.1556. Min Act: -0.0000

Data Index: 428331 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.1630. Min Act: -0.0000

Data Index: 2776 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1077803 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0841. Min Act: -0.0000

Data Index: 780235 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1167698 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1199698 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1133602 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9766. Min Act: -0.0000

Data Index: 533917 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1012553 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.8830. Min Act: -0.0000

Data Index: 692108 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9064. Min Act: -0.0000

Data Index: 116615 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9094. Min Act: -0.0000

Data Index: 700160 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.8720. Min Act: -0.0000

Data Index: 149400 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1320355 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.8717. Min Act: -0.0000

Data Index: 778535 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.8160. Min Act: -0.0000

Data Index: 275681 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1131746 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1062358 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.8645. Min Act: -0.0000

Data Index: 934852 (C4 (Web Text))

Max Activating Token Index: 117