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

Dataset: The Pile

Neuron 3184 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6471. Min Range: -5.6471

Max Act: 5.6471. Min Act: -0.0000

Data Index: 1246190 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 5.6471. Min Range: -5.6471

Max Act: 5.0182. Min Act: -0.0000

Data Index: 272964 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 5.6471. Min Range: -5.6471

Max Act: 4.6922. Min Act: -0.0000

Data Index: 1708795 (The Pile)

Max Activating Token Index: 681

Text #3

Max Range: 5.6471. Min Range: -5.6471

Max Act: 4.4919. Min Act: -0.0000

Data Index: 23757 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 5.6471. Min Range: -5.6471

Max Act: 4.2635. Min Act: -0.0000

Data Index: 1043931 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.9501. Min Act: -0.0000

Data Index: 215426 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.7569. Min Act: -0.0000

Data Index: 1999714 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.2211. Min Act: -0.0000

Data Index: 719272 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.8186. Min Act: -0.0000

Data Index: 1666613 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.5211. Min Act: -0.0000

Data Index: 1304595 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.4820. Min Act: -0.0000

Data Index: 975732 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.4788. Min Act: -0.0000

Data Index: 262525 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.4982. Min Act: -0.0000

Data Index: 846558 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.5810. Min Act: -0.0000

Data Index: 785395 (The Pile)

Max Activating Token Index: 541

Text #14

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.4234. Min Act: -0.0000

Data Index: 1883322 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 5.6471. Min Range: -5.6471

Max Act: 2.4641. Min Act: -0.0000

Data Index: 1723418 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.4108. Min Act: -0.0000

Data Index: 803266 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.1081. Min Act: -0.0000

Data Index: 1449872 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.4198. Min Act: -0.0000

Data Index: 1949607 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 5.6471. Min Range: -5.6471

Max Act: 3.0734. Min Act: -0.0000

Data Index: 1968941 (The Pile)

Max Activating Token Index: 560