Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5079 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1643. Min Act: -0.0000

Data Index: 559658 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1588563 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1879391 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1337. Min Act: 0.0000

Data Index: 43398 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1217. Min Act: -0.0000

Data Index: 974924 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1252. Min Act: 0.0000

Data Index: 857894 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1530918 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1855474 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1110. Min Act: 0.0000

Data Index: 129770 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1052. Min Act: 0.0000

Data Index: 245650 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1112. Min Act: 0.0000

Data Index: 1935241 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1022915 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1667863 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1249803 (The Pile)

Max Activating Token Index: 934

Text #14

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1811393 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1045. Min Act: -0.0000

Data Index: 56304 (The Pile)

Max Activating Token Index: 567

Text #16

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1361543 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1582341 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0935. Min Act: -0.0000

Data Index: 11419 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0907. Min Act: 0.0000

Data Index: 1820439 (The Pile)

Max Activating Token Index: 930