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

Dataset: The Pile

Neuron 4463 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: 0.6714. Min Range: -0.6714

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1136396 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6714. Min Act: -0.0000

Data Index: 961128 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1583934 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5916. Min Act: -0.0000

Data Index: 657288 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5251. Min Act: 0.0000

Data Index: 787852 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1574836 (The Pile)

Max Activating Token Index: 234

Text #6

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5257. Min Act: -0.0000

Data Index: 987358 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5259. Min Act: 0.0000

Data Index: 1306206 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1928460 (The Pile)

Max Activating Token Index: 907

Text #9

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1510368 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1760683 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1139041 (The Pile)

Max Activating Token Index: 289

Text #12

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4743. Min Act: -0.0000

Data Index: 583347 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1578628 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4218. Min Act: -0.0000

Data Index: 586261 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1796530 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4856. Min Act: -0.0000

Data Index: 60783 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4076. Min Act: -0.0000

Data Index: 264588 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4116. Min Act: -0.0000

Data Index: 232462 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4026. Min Act: -0.0000

Data Index: 754889 (The Pile)

Max Activating Token Index: 572