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

Dataset: The Pile

Neuron 1043 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.6440. Min Act: -0.0000

Data Index: 329911 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5770. Min Act: -0.0000

Data Index: 677505 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5489. Min Act: -0.0000

Data Index: 257746 (The Pile)

Max Activating Token Index: 342

Text #3

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1551991 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1518604 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1014824 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5124. Min Act: -0.0000

Data Index: 790601 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1216786 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4702. Min Act: -0.0000

Data Index: 476467 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1984540 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1779110 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4664. Min Act: 0.0000

Data Index: 822367 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1801523 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1190278 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4773. Min Act: -0.0000

Data Index: 421190 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1419709 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4693. Min Act: -0.0000

Data Index: 750432 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1602698 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1178843 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4602. Min Act: -0.0000

Data Index: 507878 (The Pile)

Max Activating Token Index: 821