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

Dataset: The Pile

Neuron 3355 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: 0.8957. Min Range: -0.8957

Max Act: 0.8957. Min Act: -0.0000

Data Index: 364177 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6111. Min Act: -0.0000

Data Index: 270858 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6037. Min Act: -0.0000

Data Index: 671141 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6102. Min Act: -0.0000

Data Index: 236769 (The Pile)

Max Activating Token Index: 978

Text #4

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1872495 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1387160 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.5901. Min Act: -0.0000

Data Index: 399674 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1144810 (The Pile)

Max Activating Token Index: 857

Text #8

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.5105. Min Act: -0.0000

Data Index: 443911 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1852819 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.5304. Min Act: -0.0000

Data Index: 262628 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1985081 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1773448 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.4860. Min Act: -0.0000

Data Index: 41012 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1806220 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.5417. Min Act: -0.0000

Data Index: 23379 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1078504 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1978373 (The Pile)

Max Activating Token Index: 689

Text #18

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.4526. Min Act: -0.0000

Data Index: 495155 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.4023. Min Act: -0.0000

Data Index: 921893 (The Pile)

Max Activating Token Index: 948