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

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

Neuron 3596 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0830. Min Range: -3.0830

Max Act: 3.0830. Min Act: -0.0000

Data Index: 210017 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.9728. Min Act: -0.0001

Data Index: 605161 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.6580. Min Act: -0.0000

Data Index: 752456 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.6242. Min Act: -0.0000

Data Index: 46597 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.4684. Min Act: -0.0000

Data Index: 1053837 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.4568. Min Act: -0.0000

Data Index: 613142 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.6364. Min Act: -0.0000

Data Index: 795116 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.4704. Min Act: -0.0000

Data Index: 328993 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.4479. Min Act: -0.0000

Data Index: 604218 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.4004. Min Act: -0.0000

Data Index: 412097 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.4181. Min Act: -0.0000

Data Index: 1139708 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.2649. Min Act: -0.0000

Data Index: 750854 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.3736. Min Act: -0.0000

Data Index: 768527 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.1043. Min Act: -0.0001

Data Index: 1257702 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.4571. Min Act: -0.0000

Data Index: 1350446 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.0864. Min Act: -0.0000

Data Index: 494462 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.2836. Min Act: -0.0000

Data Index: 392343 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.2606. Min Act: -0.0000

Data Index: 567268 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.1374. Min Act: -0.0000

Data Index: 1341505 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.2487. Min Act: -0.0001

Data Index: 601977 (C4 (Web Text))

Max Activating Token Index: 204