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

Dataset: The Pile

Neuron 2100 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: 1.5017. Min Range: -1.5017

Max Act: 1.5017. Min Act: -0.0000

Data Index: 109990 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 1.5017. Min Range: -1.5017

Max Act: 1.4480. Min Act: -0.0000

Data Index: 845137 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 1.5017. Min Range: -1.5017

Max Act: 1.1270. Min Act: -0.0000

Data Index: 351232 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 1.5017. Min Range: -1.5017

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1157184 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.9928. Min Act: -0.0000

Data Index: 389739 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1667884 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.9921. Min Act: -0.0000

Data Index: 594309 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.7916. Min Act: -0.0000

Data Index: 935813 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.7437. Min Act: -0.0000

Data Index: 872576 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1920831 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.7923. Min Act: -0.0000

Data Index: 564694 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.7159. Min Act: -0.0000

Data Index: 690429 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.7118. Min Act: -0.0000

Data Index: 192021 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1577411 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1543537 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1818334 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.6296. Min Act: -0.0000

Data Index: 875542 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.6252. Min Act: -0.0000

Data Index: 49766 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1675300 (The Pile)

Max Activating Token Index: 32

Text #19

Max Range: 1.5017. Min Range: -1.5017

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1992187 (The Pile)

Max Activating Token Index: 598