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

Dataset: The Pile

Neuron 1829 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: 3.0865. Min Range: -3.0865

Max Act: 2.8486. Min Act: -0.0000

Data Index: 1780613 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.9611. Min Act: -0.0000

Data Index: 890837 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 3.0865. Min Range: -3.0865

Max Act: 3.0865. Min Act: -0.0000

Data Index: 419938 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 3.0865. Min Range: -3.0865

Max Act: 3.0624. Min Act: -0.0000

Data Index: 1371091 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.7657. Min Act: -0.0000

Data Index: 1633500 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.8740. Min Act: -0.0000

Data Index: 1563040 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.8246. Min Act: -0.0000

Data Index: 1245046 (The Pile)

Max Activating Token Index: 629

Text #7

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.7493. Min Act: -0.0000

Data Index: 914914 (The Pile)

Max Activating Token Index: 381

Text #8

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6995. Min Act: -0.0000

Data Index: 818196 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6230. Min Act: -0.0000

Data Index: 716891 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.5182. Min Act: -0.0000

Data Index: 1226895 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.7263. Min Act: -0.0000

Data Index: 172899 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.8484. Min Act: -0.0000

Data Index: 1825228 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6803. Min Act: -0.0000

Data Index: 1978158 (The Pile)

Max Activating Token Index: 551

Text #14

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.5470. Min Act: -0.0000

Data Index: 39689 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6747. Min Act: -0.0000

Data Index: 1124248 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6535. Min Act: -0.0000

Data Index: 1135905 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.2669. Min Act: -0.0000

Data Index: 323264 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.5025. Min Act: -0.0000

Data Index: 1263889 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.4872. Min Act: -0.0000

Data Index: 725073 (The Pile)

Max Activating Token Index: 559