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

Dataset: The Pile

Neuron 1683 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1965210 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1824353 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.2456. Min Act: -0.0000

Data Index: 668236 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.1096. Min Act: -0.0000

Data Index: 808770 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1755993 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.2125. Min Act: -0.0000

Data Index: 641331 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0602. Min Act: -0.0000

Data Index: 599113 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0573. Min Act: -0.0000

Data Index: 358989 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1767733 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1451325 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0484. Min Act: -0.0000

Data Index: 831117 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0693. Min Act: -0.0000

Data Index: 376153 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0106. Min Act: -0.0000

Data Index: 771444 (The Pile)

Max Activating Token Index: 740

Text #13

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0522. Min Act: -0.0000

Data Index: 72720 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1029151 (The Pile)

Max Activating Token Index: 866

Text #15

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0416. Min Act: -0.0000

Data Index: 1700145 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.9810. Min Act: -0.0000

Data Index: 415903 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0169. Min Act: -0.0000

Data Index: 889701 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1306110 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 1.2921. Min Range: -1.2921

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1789614 (The Pile)

Max Activating Token Index: 943