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

Dataset: The Pile

Neuron 1342 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.3172. Min Act: -0.0000

Data Index: 88610 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1368812 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2322. Min Act: -0.0000

Data Index: 385724 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2004. Min Act: 0.0000

Data Index: 1107230 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2155. Min Act: -0.0000

Data Index: 67404 (The Pile)

Max Activating Token Index: 898

Text #5

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2019. Min Act: -0.0000

Data Index: 935889 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2085. Min Act: -0.0000

Data Index: 814531 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2256. Min Act: -0.0000

Data Index: 74050 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1746378 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2221. Min Act: -0.0000

Data Index: 352315 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1836. Min Act: -0.0000

Data Index: 232379 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1853036 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1022848 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1779657 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1268740 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1818225 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1970. Min Act: -0.0000

Data Index: 415098 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1840. Min Act: -0.0000

Data Index: 478401 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1710410 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1635. Min Act: -0.0000

Data Index: 220474 (The Pile)

Max Activating Token Index: 963