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

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

Neuron 4590 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.3758. Min Act: -0.0001

Data Index: 1271233 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.1731. Min Act: -0.0001

Data Index: 1025285 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0855. Min Act: -0.0001

Data Index: 929152 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.1153. Min Act: -0.0001

Data Index: 268478 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0809. Min Act: -0.0001

Data Index: 1300475 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0625. Min Act: -0.0000

Data Index: 165728 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0828. Min Act: -0.0000

Data Index: 883424 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0532. Min Act: -0.0001

Data Index: 1083186 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0511. Min Act: -0.0000

Data Index: 898910 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0570. Min Act: -0.0001

Data Index: 160299 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0508. Min Act: -0.0001

Data Index: 532613 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0429. Min Act: -0.0001

Data Index: 385795 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0614. Min Act: -0.0001

Data Index: 924675 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0715. Min Act: -0.0001

Data Index: 273540 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0423. Min Act: -0.0001

Data Index: 589505 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.3758. Min Range: -1.3758

Max Act: 0.9322. Min Act: -0.0001

Data Index: 800308 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.1055. Min Act: -0.0001

Data Index: 871981 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0026. Min Act: -0.0001

Data Index: 789268 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 1.3758. Min Range: -1.3758

Max Act: 1.0370. Min Act: -0.0000

Data Index: 954532 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 1.3758. Min Range: -1.3758

Max Act: 0.9879. Min Act: -0.0001

Data Index: 804530 (C4 (Web Text))

Max Activating Token Index: 1001