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

Dataset: The Pile

Neuron 3617 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: 0.9598. Min Range: -0.9598

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1214769 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8606. Min Act: -0.0000

Data Index: 612304 (The Pile)

Max Activating Token Index: 202

Text #2

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8859. Min Act: -0.0000

Data Index: 548153 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1707607 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8814. Min Act: 0.0000

Data Index: 389140 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7691. Min Act: -0.0000

Data Index: 407599 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1745254 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7355. Min Act: -0.0000

Data Index: 703460 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1058468 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7958. Min Act: 0.0000

Data Index: 47661 (The Pile)

Max Activating Token Index: 286

Text #10

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7517. Min Act: -0.0000

Data Index: 979222 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1975507 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7195. Min Act: -0.0000

Data Index: 704447 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1458687 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1957753 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1484524 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7446. Min Act: -0.0001

Data Index: 770730 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7138. Min Act: -0.0000

Data Index: 228519 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7177. Min Act: -0.0000

Data Index: 487804 (The Pile)

Max Activating Token Index: 202

Text #19

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1644365 (The Pile)

Max Activating Token Index: 229