Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5041 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4675. Min Act: -0.0003

Data Index: 1291994 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4807. Min Act: -0.0003

Data Index: 663540 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4822. Min Act: -0.0002

Data Index: 126529 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4600. Min Act: -0.0003

Data Index: 826898 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4423. Min Act: -0.0003

Data Index: 1189615 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4508. Min Act: -0.0002

Data Index: 494450 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4330. Min Act: -0.0002

Data Index: 386665 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4306. Min Act: -0.0003

Data Index: 911847 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4341. Min Act: -0.0003

Data Index: 480302 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4052. Min Act: -0.0002

Data Index: 998775 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4445. Min Act: -0.0003

Data Index: 960289 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4429. Min Act: -0.0002

Data Index: 1257111 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4230. Min Act: -0.0003

Data Index: 235318 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4247. Min Act: -0.0002

Data Index: 415650 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4244. Min Act: -0.0003

Data Index: 322461 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4117. Min Act: -0.0003

Data Index: 666170 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4218. Min Act: -0.0003

Data Index: 813763 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4029. Min Act: -0.0003

Data Index: 37160 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4115. Min Act: -0.0003

Data Index: 1252979 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4424. Min Act: -0.0002

Data Index: 439200 (C4 (Web Text))

Max Activating Token Index: 731