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

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

Neuron 250 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.4000. Min Act: -0.0001

Data Index: 353113 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3977. Min Act: -0.0001

Data Index: 1150666 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.4067. Min Act: -0.0001

Data Index: 1046280 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3429. Min Act: -0.0001

Data Index: 957235 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1014604 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3144. Min Act: -0.0001

Data Index: 1063922 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3086. Min Act: -0.0001

Data Index: 510340 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2963. Min Act: -0.0001

Data Index: 262780 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1271829 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2929. Min Act: -0.0001

Data Index: 1064327 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2997. Min Act: -0.0001

Data Index: 1261145 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2990. Min Act: -0.0001

Data Index: 647789 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2680. Min Act: -0.0001

Data Index: 932970 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2727. Min Act: -0.0001

Data Index: 959390 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1303802 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2560. Min Act: -0.0001

Data Index: 480886 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2676. Min Act: -0.0001

Data Index: 1156824 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2585. Min Act: -0.0001

Data Index: 1256362 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2569. Min Act: -0.0001

Data Index: 536661 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2734. Min Act: -0.0001

Data Index: 507215 (C4 (Web Text))

Max Activating Token Index: 1017