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

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

Neuron 4279 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.7879. Min Act: -0.0000

Data Index: 816885 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.7899. Min Act: -0.0000

Data Index: 810634 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.5299. Min Act: -0.0000

Data Index: 91095 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.4977. Min Act: -0.0000

Data Index: 562559 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.5156. Min Act: -0.0000

Data Index: 1053753 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.4768. Min Act: -0.0000

Data Index: 1214092 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.4374. Min Act: -0.0000

Data Index: 1127513 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.4448. Min Act: -0.0000

Data Index: 1098553 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.3103. Min Act: -0.0000

Data Index: 926739 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.2854. Min Act: -0.0000

Data Index: 491837 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.2681. Min Act: -0.0000

Data Index: 1054406 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.2619. Min Act: -0.0000

Data Index: 12533 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.1181. Min Act: -0.0000

Data Index: 771359 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.1719. Min Act: -0.0000

Data Index: 1330217 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.1371. Min Act: -0.0000

Data Index: 980328 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.1373. Min Act: -0.0000

Data Index: 577220 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.1228. Min Act: -0.0000

Data Index: 1088482 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.0970. Min Act: -0.0000

Data Index: 1327588 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 2.7899. Min Range: -2.7899

Max Act: 1.9601. Min Act: -0.0000

Data Index: 403234 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 2.7899. Min Range: -2.7899

Max Act: 2.0711. Min Act: -0.0000

Data Index: 212556 (C4 (Web Text))

Max Activating Token Index: 165