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

Dataset: The Pile

Neuron 2870 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0149. Min Act: 0.0000

Data Index: 185687 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0132. Min Act: -0.0000

Data Index: 665653 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0126. Min Act: 0.0000

Data Index: 1991611 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0124. Min Act: -0.0000

Data Index: 921326 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0119. Min Act: -0.0000

Data Index: 1759452 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0118. Min Act: -0.0000

Data Index: 150615 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0114. Min Act: -0.0000

Data Index: 906044 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0109. Min Act: -0.0000

Data Index: 932970 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0113. Min Act: -0.0000

Data Index: 1418798 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0115. Min Act: -0.0000

Data Index: 1965234 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0111. Min Act: -0.0000

Data Index: 99490 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0108. Min Act: 0.0000

Data Index: 286647 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1689157 (The Pile)

Max Activating Token Index: 873

Text #13

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0107. Min Act: -0.0000

Data Index: 384941 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0107. Min Act: -0.0000

Data Index: 475931 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0107. Min Act: -0.0000

Data Index: 317915 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0105. Min Act: -0.0000

Data Index: 1212057 (The Pile)

Max Activating Token Index: 699

Text #17

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0104. Min Act: -0.0000

Data Index: 1566265 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0104. Min Act: -0.0000

Data Index: 324035 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0103. Min Act: -0.0000

Data Index: 618981 (The Pile)

Max Activating Token Index: 758