Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 231 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.8073. Min Act: -0.0000

Data Index: 658872 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1808132 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6083. Min Act: -0.0000

Data Index: 714172 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1724257 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1918938 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1180328 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5805. Min Act: -0.0000

Data Index: 758315 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5317. Min Act: -0.0000

Data Index: 200253 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1751292 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1649350 (The Pile)

Max Activating Token Index: 765

Text #10

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1692480 (The Pile)

Max Activating Token Index: 20

Text #11

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1844763 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4659. Min Act: -0.0000

Data Index: 64593 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1356006 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4998. Min Act: -0.0000

Data Index: 269352 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4899. Min Act: -0.0000

Data Index: 197319 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4787. Min Act: -0.0000

Data Index: 613116 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1040156 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4181. Min Act: -0.0000

Data Index: 751431 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4744. Min Act: -0.0000

Data Index: 214661 (The Pile)

Max Activating Token Index: 261