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

Dataset: The Pile

Neuron 2040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.9012. Min Act: -0.0000

Data Index: 254217 (The Pile)

Max Activating Token Index: 783

Text #1

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1926450 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8095. Min Act: -0.0000

Data Index: 935651 (The Pile)

Max Activating Token Index: 174

Text #3

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1912004 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1455762 (The Pile)

Max Activating Token Index: 719

Text #5

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1712571 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8000. Min Act: -0.0000

Data Index: 871022 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7427. Min Act: -0.0000

Data Index: 699424 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1204225 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7455. Min Act: -0.0000

Data Index: 553996 (The Pile)

Max Activating Token Index: 933

Text #10

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1827917 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7123. Min Act: -0.0000

Data Index: 884212 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1249275 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7268. Min Act: -0.0000

Data Index: 212209 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1396476 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7445. Min Act: -0.0000

Data Index: 502753 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7030. Min Act: -0.0000

Data Index: 268342 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1374500 (The Pile)

Max Activating Token Index: 47

Text #18

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1962185 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1557196 (The Pile)

Max Activating Token Index: 513