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

Dataset: The Pile

Neuron 2819 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: 1.1913. Min Range: -1.1913

Max Act: 1.1913. Min Act: -0.0000

Data Index: 647149 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 1.1913. Min Range: -1.1913

Max Act: 1.0668. Min Act: -0.0000

Data Index: 121030 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 1.1913. Min Range: -1.1913

Max Act: 1.1131. Min Act: -0.0000

Data Index: 841963 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 1.1913. Min Range: -1.1913

Max Act: 1.0456. Min Act: -0.0000

Data Index: 45442 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 1.1913. Min Range: -1.1913

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1137565 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1452393 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8932. Min Act: 0.0001

Data Index: 1413239 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.9170. Min Act: 0.0000

Data Index: 712764 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1852438 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8435. Min Act: -0.0000

Data Index: 1160815 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8463. Min Act: -0.0000

Data Index: 8907 (The Pile)

Max Activating Token Index: 314

Text #11

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8921. Min Act: -0.0000

Data Index: 599974 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8789. Min Act: 0.0000

Data Index: 922732 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8124. Min Act: 0.0000

Data Index: 1039525 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1333267 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8301. Min Act: -0.0000

Data Index: 28889 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8471. Min Act: -0.0000

Data Index: 193321 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8096. Min Act: 0.0000

Data Index: 431703 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1421602 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8194. Min Act: -0.0000

Data Index: 475936 (The Pile)

Max Activating Token Index: 110