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

Dataset: The Pile

Neuron 1381 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: 0.7374. Min Range: -0.7374

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1783355 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6753. Min Act: -0.0000

Data Index: 110032 (The Pile)

Max Activating Token Index: 374

Text #2

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6963. Min Act: -0.0000

Data Index: 74933 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1685983 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1868023 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6829. Min Act: -0.0000

Data Index: 440116 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5498. Min Act: -0.0000

Data Index: 276835 (The Pile)

Max Activating Token Index: 626

Text #7

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6425. Min Act: -0.0000

Data Index: 10187 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6480. Min Act: -0.0000

Data Index: 215949 (The Pile)

Max Activating Token Index: 602

Text #9

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1473102 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.7036. Min Act: -0.0000

Data Index: 740751 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1734878 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1912494 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1132051 (The Pile)

Max Activating Token Index: 987

Text #14

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1151861 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5848. Min Act: -0.0000

Data Index: 324683 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1480375 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6629. Min Act: -0.0000

Data Index: 981607 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5788. Min Act: -0.0000

Data Index: 206679 (The Pile)

Max Activating Token Index: 40

Text #19

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5647. Min Act: -0.0000

Data Index: 13908 (The Pile)

Max Activating Token Index: 1008