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

Dataset: The Pile

Neuron 31 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5775. Min Act: -0.0000

Data Index: 330052 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5715. Min Act: -0.0000

Data Index: 189147 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1775247 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1004720 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5286. Min Act: -0.0000

Data Index: 483053 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1633530 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5321. Min Act: -0.0000

Data Index: 466184 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1797931 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5748. Min Act: -0.0000

Data Index: 814272 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5467. Min Act: -0.0000

Data Index: 559294 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5290. Min Act: -0.0000

Data Index: 251310 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5072. Min Act: -0.0000

Data Index: 671956 (The Pile)

Max Activating Token Index: 585

Text #12

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4758. Min Act: -0.0000

Data Index: 390170 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1694758 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4700. Min Act: -0.0000

Data Index: 785881 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1083 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1264593 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4896. Min Act: -0.0000

Data Index: 879691 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4736. Min Act: -0.0000

Data Index: 820491 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1148784 (The Pile)

Max Activating Token Index: 243