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

Dataset: The Pile

Neuron 581 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: 0.1811. Min Range: -0.1811

Max Act: 0.1811. Min Act: -0.0000

Data Index: 374026 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1098691 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1267082 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0978. Min Act: -0.0000

Data Index: 913712 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1037246 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1088. Min Act: -0.0000

Data Index: 476563 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1562. Min Act: -0.0000

Data Index: 966052 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1420. Min Act: -0.0000

Data Index: 802954 (The Pile)

Max Activating Token Index: 977

Text #8

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1176. Min Act: -0.0000

Data Index: 413541 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1002851 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0943. Min Act: -0.0000

Data Index: 67887 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1272290 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1095. Min Act: -0.0000

Data Index: 794959 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1025. Min Act: -0.0000

Data Index: 650400 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0947. Min Act: -0.0000

Data Index: 322627 (The Pile)

Max Activating Token Index: 624

Text #15

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0914. Min Act: -0.0000

Data Index: 526779 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1217216 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0810. Min Act: -0.0000

Data Index: 694869 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1157214 (The Pile)

Max Activating Token Index: 864

Text #19

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1102032 (The Pile)

Max Activating Token Index: 1011