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

Dataset: The Pile

Neuron 4024 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: 5.4679. Min Range: -5.4679

Max Act: 4.8489. Min Act: -0.0000

Data Index: 1803899 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 5.4679. Min Range: -5.4679

Max Act: 5.3798. Min Act: -0.0000

Data Index: 766904 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 5.4679. Min Range: -5.4679

Max Act: 5.1690. Min Act: -0.0000

Data Index: 594378 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 5.4679. Min Range: -5.4679

Max Act: 5.1367. Min Act: -0.0000

Data Index: 1430777 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 5.4679. Min Range: -5.4679

Max Act: 5.0832. Min Act: -0.0000

Data Index: 573411 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 5.4679. Min Range: -5.4679

Max Act: 5.0009. Min Act: -0.0000

Data Index: 1208730 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 5.4679. Min Range: -5.4679

Max Act: 5.2821. Min Act: -0.0000

Data Index: 19262 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 5.4679. Min Range: -5.4679

Max Act: 5.4679. Min Act: -0.0000

Data Index: 1604986 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 5.4679. Min Range: -5.4679

Max Act: 5.0731. Min Act: -0.0000

Data Index: 1923367 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.8216. Min Act: -0.0000

Data Index: 1004787 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.9907. Min Act: -0.0000

Data Index: 206433 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.4182. Min Act: -0.0000

Data Index: 1864409 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.7177. Min Act: -0.0000

Data Index: 1713380 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.2998. Min Act: -0.0000

Data Index: 1233367 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 5.4679. Min Range: -5.4679

Max Act: 5.0710. Min Act: -0.0000

Data Index: 235322 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.0936. Min Act: -0.0000

Data Index: 421147 (The Pile)

Max Activating Token Index: 95

Text #16

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.6131. Min Act: -0.0000

Data Index: 380326 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.6029. Min Act: -0.0000

Data Index: 550752 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.5485. Min Act: -0.0000

Data Index: 1726925 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 5.4679. Min Range: -5.4679

Max Act: 4.5191. Min Act: -0.0000

Data Index: 1172562 (The Pile)

Max Activating Token Index: 566