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

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

Neuron 998 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: 1.4224. Min Range: -1.4224

Max Act: 1.2423. Min Act: -0.0001

Data Index: 495604 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.4224. Min Act: -0.0001

Data Index: 1098574 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2578. Min Act: -0.0000

Data Index: 469607 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.1518. Min Act: -0.0001

Data Index: 512660 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.2866. Min Act: -0.0001

Data Index: 348542 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.0155. Min Act: -0.0000

Data Index: 488442 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.9720. Min Act: -0.0001

Data Index: 381074 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.0379. Min Act: -0.0001

Data Index: 667214 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.4224. Min Range: -1.4224

Max Act: 1.0602. Min Act: -0.0000

Data Index: 942365 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.8733. Min Act: -0.0000

Data Index: 794643 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.9342. Min Act: -0.0001

Data Index: 214955 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.9363. Min Act: -0.0001

Data Index: 618931 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.9375. Min Act: -0.0001

Data Index: 1174748 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.9340. Min Act: -0.0001

Data Index: 244344 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.9049. Min Act: -0.0001

Data Index: 18075 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.9291. Min Act: -0.0001

Data Index: 349733 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.8798. Min Act: -0.0000

Data Index: 677891 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.9193. Min Act: -0.0001

Data Index: 32880 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.8919. Min Act: -0.0000

Data Index: 77701 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 1.4224. Min Range: -1.4224

Max Act: 0.7710. Min Act: -0.0001

Data Index: 331801 (C4 (Web Text))

Max Activating Token Index: 842