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

Dataset: The Pile

Neuron 2419 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1415317 (The Pile)

Max Activating Token Index: 948

Text #1

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1048133 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2155. Min Act: -0.0000

Data Index: 845624 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1788376 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1492975 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1730. Min Act: -0.0000

Data Index: 210184 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1846460 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1643. Min Act: -0.0000

Data Index: 242284 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1989345 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1450. Min Act: -0.0000

Data Index: 719453 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1951344 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1379431 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1652194 (The Pile)

Max Activating Token Index: 932

Text #13

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1309. Min Act: -0.0000

Data Index: 36209 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1524041 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1868108 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1993134 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1348. Min Act: -0.0000

Data Index: 419930 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1102. Min Act: -0.0000

Data Index: 259976 (The Pile)

Max Activating Token Index: 750

Text #19

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1468. Min Act: -0.0000

Data Index: 655120 (The Pile)

Max Activating Token Index: 833