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

Dataset: The Pile

Neuron 2091 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0122. Min Range: -1.0122

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1703467 (The Pile)

Max Activating Token Index: 450

Text #1

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1646962 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1617695 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1538345 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7346. Min Act: -0.0000

Data Index: 732242 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1689443 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7112. Min Act: -0.0000

Data Index: 991663 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7177. Min Act: -0.0000

Data Index: 995827 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1931144 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6195. Min Act: -0.0000

Data Index: 977875 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1353694 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1881056 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.5950. Min Act: -0.0000

Data Index: 494778 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1355456 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1820605 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1602415 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6016. Min Act: -0.0000

Data Index: 518460 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1183608 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.5807. Min Act: -0.0000

Data Index: 575766 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1009440 (The Pile)

Max Activating Token Index: 749