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

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

Neuron 5398 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1007562 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1171. Min Act: -0.0000

Data Index: 876206 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1194. Min Act: -0.0000

Data Index: 977777 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1165. Min Act: -0.0000

Data Index: 345260 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1157015 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0842. Min Act: -0.0000

Data Index: 469883 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1344665 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0815. Min Act: -0.0000

Data Index: 3867 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0850. Min Act: -0.0000

Data Index: 918414 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0781. Min Act: -0.0000

Data Index: 478671 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0750. Min Act: -0.0000

Data Index: 91851 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1058604 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0738. Min Act: -0.0000

Data Index: 939870 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0768. Min Act: -0.0000

Data Index: 365621 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1265374 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1645421 (Python Code)

Max Activating Token Index: 755

Text #16

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1024. Min Act: -0.0000

Data Index: 358543 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0811. Min Act: -0.0000

Data Index: 781083 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0749. Min Act: -0.0000

Data Index: 299218 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0765. Min Act: -0.0000

Data Index: 625072 (C4 (Web Text))

Max Activating Token Index: 780