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

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

Neuron 3916 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2817. Min Range: -1.2817

Max Act: 1.2817. Min Act: -0.0000

Data Index: 584717 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 1.2817. Min Range: -1.2817

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1154867 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.2817. Min Range: -1.2817

Max Act: 1.0077. Min Act: 0.0000

Data Index: 7886 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.2817. Min Range: -1.2817

Max Act: 1.0102. Min Act: -0.0000

Data Index: 913863 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.9161. Min Act: -0.0000

Data Index: 110412 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1153351 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.8384. Min Act: 0.0000

Data Index: 1069455 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1071691 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1093559 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.8892. Min Act: -0.0000

Data Index: 762256 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.8555. Min Act: -0.0000

Data Index: 204093 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1326138 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.8513. Min Act: -0.0000

Data Index: 853422 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.8467. Min Act: -0.0000

Data Index: 774865 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.8698. Min Act: -0.0000

Data Index: 64088 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.7816. Min Act: -0.0000

Data Index: 710814 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.7323. Min Act: -0.0000

Data Index: 851686 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.6969. Min Act: -0.0000

Data Index: 560273 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.7660. Min Act: -0.0000

Data Index: 78172 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.2817. Min Range: -1.2817

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1019495 (C4 (Web Text))

Max Activating Token Index: 413