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

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

Neuron 5812 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: 1.5693. Min Range: -1.5693

Max Act: 1.5693. Min Act: -0.0000

Data Index: 1161323 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.2473. Min Act: 0.0000

Data Index: 802583 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.2556. Min Act: -0.0000

Data Index: 770382 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.2704. Min Act: 0.0000

Data Index: 726755 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.2614. Min Act: -0.0000

Data Index: 1173841 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.1275. Min Act: -0.0000

Data Index: 774336 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.0462. Min Act: -0.0000

Data Index: 779305 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1114160 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.0251. Min Act: 0.0000

Data Index: 1285728 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.0964. Min Act: 0.0000

Data Index: 370069 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1069229 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.0713. Min Act: -0.0000

Data Index: 797293 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 1.5693. Min Range: -1.5693

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1347782 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 1.5693. Min Range: -1.5693

Max Act: 0.9837. Min Act: 0.0000

Data Index: 649499 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.5693. Min Range: -1.5693

Max Act: 0.9791. Min Act: -0.0000

Data Index: 273097 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 1.5693. Min Range: -1.5693

Max Act: 1.0253. Min Act: 0.0000

Data Index: 549188 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.5693. Min Range: -1.5693

Max Act: 0.9612. Min Act: 0.0000

Data Index: 1321288 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 1.5693. Min Range: -1.5693

Max Act: 0.9020. Min Act: -0.0000

Data Index: 319399 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 1.5693. Min Range: -1.5693

Max Act: 0.9394. Min Act: -0.0000

Data Index: 512120 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 1.5693. Min Range: -1.5693

Max Act: 0.9317. Min Act: -0.0000

Data Index: 568414 (C4 (Web Text))

Max Activating Token Index: 738