Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2864 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2246. Min Act: -0.0000

Data Index: 754491 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2127. Min Act: -0.0000

Data Index: 372801 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1005255 (The Pile)

Max Activating Token Index: 914

Text #3

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1777671 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2245. Min Act: -0.0000

Data Index: 790425 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1018679 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2104. Min Act: -0.0000

Data Index: 428934 (The Pile)

Max Activating Token Index: 805

Text #7

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1124052 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2051. Min Act: -0.0000

Data Index: 134814 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1461569 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1330522 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2019. Min Act: -0.0000

Data Index: 218091 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1869. Min Act: -0.0000

Data Index: 702398 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1492967 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1066670 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1129929 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1003696 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1612. Min Act: -0.0000

Data Index: 601434 (The Pile)

Max Activating Token Index: 915

Text #18

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1404366 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1545444 (The Pile)

Max Activating Token Index: 320