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

Dataset: The Pile

Neuron 2569 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.2092. Min Act: -0.0000

Data Index: 1540965 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.1607. Min Act: -0.0000

Data Index: 183139 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1965537 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0675. Min Act: -0.0000

Data Index: 139461 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1372900 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0458. Min Act: -0.0000

Data Index: 1162978 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1609192 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9754. Min Act: -0.0000

Data Index: 898419 (The Pile)

Max Activating Token Index: 432

Text #8

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0337. Min Act: -0.0000

Data Index: 139548 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9083. Min Act: -0.0000

Data Index: 271429 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8107. Min Act: -0.0000

Data Index: 457553 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0617. Min Act: -0.0000

Data Index: 939528 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1542031 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1421193 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9263. Min Act: -0.0000

Data Index: 249394 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9778. Min Act: -0.0000

Data Index: 253401 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1508646 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1171391 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1085891 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1894553 (The Pile)

Max Activating Token Index: 184