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

Dataset: The Pile

Neuron 910 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5425. Min Act: -0.0000

Data Index: 970545 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.6017. Min Act: -0.0000

Data Index: 721415 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.6401. Min Act: -0.0000

Data Index: 135934 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5781. Min Act: -0.0000

Data Index: 750686 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1544570 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5177. Min Act: -0.0000

Data Index: 775347 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1232319 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1752542 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5506. Min Act: -0.0000

Data Index: 950619 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1798895 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1224674 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1065175 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1618072 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5331. Min Act: -0.0000

Data Index: 22362 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5530. Min Act: -0.0000

Data Index: 253357 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1979209 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5212. Min Act: -0.0000

Data Index: 887573 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5024. Min Act: -0.0000

Data Index: 891397 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1641157 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1438937 (The Pile)

Max Activating Token Index: 357