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

Dataset: The Pile

Neuron 1293 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: 1.1048. Min Range: -1.1048

Max Act: 0.9512. Min Act: -0.0000

Data Index: 481099 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 1.1048. Min Range: -1.1048

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1559399 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 1.1048. Min Range: -1.1048

Max Act: 1.1048. Min Act: -0.0000

Data Index: 255425 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 1.1048. Min Range: -1.1048

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1524985 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 1.1048. Min Range: -1.1048

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1510108 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1615898 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1521408 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 1.1048. Min Range: -1.1048

Max Act: 1.0365. Min Act: -0.0000

Data Index: 1505482 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1839691 (The Pile)

Max Activating Token Index: 693

Text #9

Max Range: 1.1048. Min Range: -1.1048

Max Act: 1.0081. Min Act: -0.0000

Data Index: 1605787 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.8832. Min Act: -0.0000

Data Index: 666469 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.9307. Min Act: -0.0000

Data Index: 93204 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.9130. Min Act: -0.0000

Data Index: 862486 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1477011 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1411899 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.9125. Min Act: -0.0000

Data Index: 978556 (The Pile)

Max Activating Token Index: 605

Text #16

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1000524 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.8902. Min Act: -0.0000

Data Index: 128727 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1292723 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 1.1048. Min Range: -1.1048

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1247294 (The Pile)

Max Activating Token Index: 656