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

Dataset: The Pile

Neuron 4582 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.7447. Min Act: -0.0000

Data Index: 840095 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1774672 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.7072. Min Act: -0.0000

Data Index: 860097 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.6221. Min Act: -0.0000

Data Index: 332966 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1243107 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5877. Min Act: -0.0000

Data Index: 203651 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1379637 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1565344 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1479887 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1125399 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5191. Min Act: -0.0000

Data Index: 63239 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5186. Min Act: -0.0000

Data Index: 842500 (The Pile)

Max Activating Token Index: 771

Text #12

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5078. Min Act: -0.0000

Data Index: 83732 (The Pile)

Max Activating Token Index: 16

Text #13

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1514469 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5067. Min Act: -0.0000

Data Index: 43555 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.5028. Min Act: -0.0000

Data Index: 932357 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.4856. Min Act: -0.0000

Data Index: 811077 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1746893 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.4700. Min Act: -0.0000

Data Index: 276934 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 0.7447. Min Range: -0.7447

Max Act: 0.4833. Min Act: -0.0000

Data Index: 828757 (The Pile)

Max Activating Token Index: 288