Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1185 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.3343. Min Act: -0.0004

Data Index: 126250 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2232. Min Act: -0.0004

Data Index: 81983 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2373. Min Act: -0.0004

Data Index: 956510 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2258. Min Act: -0.0004

Data Index: 1020331 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2109. Min Act: -0.0004

Data Index: 276913 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1966. Min Act: -0.0004

Data Index: 254342 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1938. Min Act: -0.0004

Data Index: 535045 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1915. Min Act: -0.0004

Data Index: 165894 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1819. Min Act: -0.0004

Data Index: 3065 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1834. Min Act: -0.0004

Data Index: 533821 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1894. Min Act: -0.0004

Data Index: 820138 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1833. Min Act: -0.0004

Data Index: 115848 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1865. Min Act: -0.0004

Data Index: 245684 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1664. Min Act: -0.0004

Data Index: 882075 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1715. Min Act: -0.0004

Data Index: 925813 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1606. Min Act: -0.0004

Data Index: 759134 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1803. Min Act: -0.0004

Data Index: 953756 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1640. Min Act: -0.0004

Data Index: 695750 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1588. Min Act: -0.0004

Data Index: 552280 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.1629. Min Act: -0.0004

Data Index: 756774 (C4 (Web Text))

Max Activating Token Index: 868