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

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

Neuron 1894 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: 1.7756. Min Range: -1.7756

Max Act: 1.7756. Min Act: -0.0000

Data Index: 1048639 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7722. Min Act: -0.0000

Data Index: 372827 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.6076. Min Act: -0.0000

Data Index: 324940 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.4388. Min Act: -0.0000

Data Index: 1105444 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.5144. Min Act: -0.0000

Data Index: 1230899 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.3843. Min Act: -0.0000

Data Index: 838422 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.3645. Min Act: -0.0000

Data Index: 1021958 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.2490. Min Act: -0.0000

Data Index: 843108 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.3201. Min Act: -0.0000

Data Index: 716268 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.3086. Min Act: -0.0000

Data Index: 1114539 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.3157. Min Act: -0.0000

Data Index: 75733 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.3006. Min Act: -0.0000

Data Index: 163347 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.2849. Min Act: -0.0000

Data Index: 137954 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.2658. Min Act: -0.0000

Data Index: 1119960 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1102810 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1083955 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.3180. Min Act: -0.0000

Data Index: 119304 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.1570. Min Act: -0.0000

Data Index: 96698 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.1849. Min Act: -0.0000

Data Index: 547686 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.2512. Min Act: -0.0000

Data Index: 842657 (C4 (Web Text))

Max Activating Token Index: 942