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

Dataset: The Pile

Neuron 3866 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: 0.2267. Min Range: -0.2267

Max Act: 0.2267. Min Act: -0.0000

Data Index: 452018 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1686464 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2083. Min Act: -0.0000

Data Index: 550277 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1880388 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1975560 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1066108 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1871. Min Act: -0.0000

Data Index: 941334 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1760. Min Act: 0.0000

Data Index: 382632 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1444661 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1788437 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1014192 (The Pile)

Max Activating Token Index: 771

Text #11

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1989861 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1077684 (The Pile)

Max Activating Token Index: 985

Text #13

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1671. Min Act: -0.0000

Data Index: 589042 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1640407 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1674. Min Act: -0.0000

Data Index: 725719 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1784. Min Act: -0.0000

Data Index: 286427 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1509688 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1653. Min Act: -0.0000

Data Index: 274625 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 0.2267. Min Range: -0.2267

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1506541 (The Pile)

Max Activating Token Index: 666