Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1760 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2220. Min Act: -0.0000

Data Index: 677539 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2085. Min Act: -0.0000

Data Index: 996675 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1311802 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2174. Min Act: -0.0001

Data Index: 156786 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1994. Min Act: -0.0000

Data Index: 540667 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2122. Min Act: -0.0001

Data Index: 194883 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1310714 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1449932 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1822. Min Act: -0.0000

Data Index: 128150 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1861. Min Act: -0.0000

Data Index: 140557 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1264586 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1739. Min Act: -0.0001

Data Index: 972445 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1791. Min Act: -0.0000

Data Index: 197395 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1817. Min Act: -0.0000

Data Index: 410898 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1553. Min Act: -0.0000

Data Index: 133490 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1750. Min Act: -0.0000

Data Index: 716535 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1683. Min Act: -0.0001

Data Index: 136485 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1670. Min Act: -0.0000

Data Index: 689278 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1226658 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1696. Min Act: -0.0000

Data Index: 917380 (C4 (Web Text))

Max Activating Token Index: 796