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

Dataset: The Pile

Neuron 346 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: 1.4162. Min Range: -1.4162

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1014307 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1493303 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.3657. Min Act: -0.0000

Data Index: 1926785 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1506373 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.3156. Min Act: -0.0000

Data Index: 208909 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1931031 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2754. Min Act: -0.0000

Data Index: 587571 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1609. Min Act: -0.0000

Data Index: 800734 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1918. Min Act: -0.0000

Data Index: 15686 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1657093 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1568830 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2043. Min Act: -0.0000

Data Index: 450964 (The Pile)

Max Activating Token Index: 880

Text #12

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1624223 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1961. Min Act: -0.0000

Data Index: 1803524 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1975141 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1837. Min Act: -0.0000

Data Index: 378606 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1596. Min Act: -0.0000

Data Index: 1609706 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2059. Min Act: -0.0000

Data Index: 866032 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.0639. Min Act: -0.0000

Data Index: 40177 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1374. Min Act: -0.0000

Data Index: 1258504 (The Pile)

Max Activating Token Index: 154