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

Dataset: The Pile

Neuron 1980 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1568441 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1477815 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2481. Min Act: -0.0000

Data Index: 865113 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1965. Min Act: -0.0000

Data Index: 537481 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2128. Min Act: -0.0000

Data Index: 585183 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1910. Min Act: -0.0000

Data Index: 762501 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1398211 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2401. Min Act: -0.0000

Data Index: 459348 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2104. Min Act: -0.0000

Data Index: 685443 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2092. Min Act: -0.0000

Data Index: 701319 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1341942 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2137. Min Act: -0.0000

Data Index: 549140 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1184878 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2102. Min Act: -0.0000

Data Index: 830004 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1354411 (The Pile)

Max Activating Token Index: 788

Text #15

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1928. Min Act: -0.0000

Data Index: 136171 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2050. Min Act: -0.0000

Data Index: 383041 (The Pile)

Max Activating Token Index: 913

Text #17

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1863. Min Act: -0.0000

Data Index: 155423 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1239684 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1649167 (The Pile)

Max Activating Token Index: 863