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

Dataset: The Pile

Neuron 2119 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: 1.7094. Min Range: -1.7094

Max Act: 1.6908. Min Act: -0.0000

Data Index: 147122 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1626280 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5434. Min Act: -0.0000

Data Index: 430312 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4380. Min Act: -0.0000

Data Index: 843732 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4134. Min Act: -0.0000

Data Index: 85858 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4353. Min Act: -0.0000

Data Index: 108562 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3186. Min Act: -0.0000

Data Index: 391184 (The Pile)

Max Activating Token Index: 744

Text #7

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1910744 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4179. Min Act: -0.0000

Data Index: 106443 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.7094. Min Act: -0.0000

Data Index: 1209086 (The Pile)

Max Activating Token Index: 842

Text #10

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3491. Min Act: -0.0000

Data Index: 1804561 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3991. Min Act: -0.0000

Data Index: 137849 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5491. Min Act: -0.0000

Data Index: 1941303 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1727574 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4260. Min Act: -0.0000

Data Index: 537279 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4661. Min Act: -0.0000

Data Index: 554614 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4137. Min Act: -0.0000

Data Index: 261127 (The Pile)

Max Activating Token Index: 733

Text #17

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1346294 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1366850 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1906812 (The Pile)

Max Activating Token Index: 136