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

Dataset: The Pile

Neuron 2649 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: 1.5756. Min Range: -1.5756

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1933132 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.4429. Min Act: -0.0000

Data Index: 1371598 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1849214 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.2174. Min Act: -0.0000

Data Index: 491231 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1888. Min Act: -0.0000

Data Index: 245474 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9186. Min Act: -0.0000

Data Index: 490837 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1570. Min Act: -0.0000

Data Index: 703425 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0025. Min Act: -0.0000

Data Index: 112889 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1878. Min Act: -0.0000

Data Index: 322866 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1643388 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1107. Min Act: -0.0000

Data Index: 1035246 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0171. Min Act: -0.0000

Data Index: 93039 (The Pile)

Max Activating Token Index: 474

Text #12

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0175. Min Act: -0.0000

Data Index: 153580 (The Pile)

Max Activating Token Index: 241

Text #13

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0232. Min Act: -0.0000

Data Index: 362479 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9083. Min Act: -0.0000

Data Index: 193262 (The Pile)

Max Activating Token Index: 196

Text #15

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1330328 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1997273 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1047993 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1401876 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9096. Min Act: -0.0000

Data Index: 564998 (The Pile)

Max Activating Token Index: 130