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

Dataset: The Pile

Neuron 3012 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: 0.3038. Min Range: -0.3038

Max Act: 0.3038. Min Act: -0.0000

Data Index: 138487 (The Pile)

Max Activating Token Index: 922

Text #1

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2373. Min Act: -0.0000

Data Index: 465319 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2334. Min Act: -0.0000

Data Index: 832554 (The Pile)

Max Activating Token Index: 761

Text #3

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1652849 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1024306 (The Pile)

Max Activating Token Index: 856

Text #5

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1298939 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1154332 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2091. Min Act: -0.0000

Data Index: 148246 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1912. Min Act: -0.0000

Data Index: 306787 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1201367 (The Pile)

Max Activating Token Index: 390

Text #10

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1986865 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1951. Min Act: -0.0000

Data Index: 296679 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1845. Min Act: -0.0000

Data Index: 385981 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1826. Min Act: -0.0000

Data Index: 920311 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1883. Min Act: -0.0000

Data Index: 624346 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1546713 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1858. Min Act: -0.0000

Data Index: 310876 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1851. Min Act: -0.0000

Data Index: 367979 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1854434 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1727369 (The Pile)

Max Activating Token Index: 252