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

Dataset: The Pile

Neuron 2836 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4806. Min Range: -6.4806

Max Act: 6.4806. Min Act: -0.0000

Data Index: 90150 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.8224. Min Act: -0.0000

Data Index: 72477 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.8280. Min Act: -0.0000

Data Index: 1781663 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.2274. Min Act: -0.0000

Data Index: 627932 (The Pile)

Max Activating Token Index: 807

Text #4

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.5479. Min Act: -0.0000

Data Index: 347455 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.3292. Min Act: -0.0000

Data Index: 1539081 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.5977. Min Act: -0.0000

Data Index: 1245293 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.4933. Min Act: -0.0000

Data Index: 1006967 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.2852. Min Act: -0.0000

Data Index: 602828 (The Pile)

Max Activating Token Index: 668

Text #9

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.2630. Min Act: -0.0000

Data Index: 1114147 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.4085. Min Act: -0.0000

Data Index: 1412261 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.4021. Min Act: -0.0000

Data Index: 1527272 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.2209. Min Act: -0.0000

Data Index: 1307367 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.1933. Min Act: -0.0000

Data Index: 1253759 (The Pile)

Max Activating Token Index: 871

Text #14

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.5055. Min Act: -0.0000

Data Index: 1094579 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.1033. Min Act: -0.0000

Data Index: 1122652 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.2721. Min Act: -0.0000

Data Index: 643273 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.2452. Min Act: -0.0000

Data Index: 569916 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.2441. Min Act: -0.0000

Data Index: 1571752 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 6.4806. Min Range: -6.4806

Max Act: 5.2145. Min Act: -0.0000

Data Index: 1285347 (The Pile)

Max Activating Token Index: 952