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

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

Neuron 4309 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1734. Min Act: -0.0000

Data Index: 243779 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.9970. Min Act: 0.0000

Data Index: 546881 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.9759. Min Act: 0.0001

Data Index: 409774 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.9308. Min Act: -0.0000

Data Index: 778931 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1336024 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.8757. Min Act: -0.0000

Data Index: 325095 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1109411 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7511. Min Act: -0.0000

Data Index: 588910 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1010870 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1329974 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7204. Min Act: -0.0000

Data Index: 264341 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7361. Min Act: -0.0000

Data Index: 253227 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7283. Min Act: -0.0000

Data Index: 383952 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7338. Min Act: -0.0000

Data Index: 500168 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7276. Min Act: -0.0000

Data Index: 730928 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7245. Min Act: -0.0000

Data Index: 429594 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7490. Min Act: 0.0001

Data Index: 1057040 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.7067. Min Act: -0.0000

Data Index: 551194 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1248612 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 1.1734. Min Range: -1.1734

Max Act: 0.6871. Min Act: 0.0000

Data Index: 1066932 (C4 (Web Text))

Max Activating Token Index: 264