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

Dataset: The Pile

Neuron 4371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.8044. Min Act: -0.0000

Data Index: 283806 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3210. Min Act: -0.0000

Data Index: 1299193 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3387. Min Act: -0.0000

Data Index: 972062 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1695934 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1359093 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1483852 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1961. Min Act: -0.0000

Data Index: 833842 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1601495 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1445. Min Act: -0.0000

Data Index: 703370 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1773717 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1351744 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1833897 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1642609 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1625621 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1505034 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2124. Min Act: -0.0000

Data Index: 284393 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1581716 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2095. Min Act: -0.0000

Data Index: 783824 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3125. Min Act: -0.0000

Data Index: 635772 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1476591 (The Pile)

Max Activating Token Index: 534