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

Dataset: The Pile

Neuron 1452 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: 1.6103. Min Range: -1.6103

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1504993 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.6103. Min Act: -0.0000

Data Index: 85208 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.3754. Min Act: -0.0000

Data Index: 1745902 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.3748. Min Act: -0.0000

Data Index: 1594895 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1870735 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1687. Min Act: -0.0000

Data Index: 908463 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1362. Min Act: -0.0000

Data Index: 464895 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1261303 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1024205 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1062520 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1720334 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1454622 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1170402 (The Pile)

Max Activating Token Index: 391

Text #13

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.0328. Min Act: -0.0000

Data Index: 86137 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1871. Min Act: -0.0000

Data Index: 1999756 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1538456 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1676. Min Act: -0.0000

Data Index: 400846 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1925649 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.0872. Min Act: -0.0000

Data Index: 698011 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.1041. Min Act: -0.0000

Data Index: 640616 (The Pile)

Max Activating Token Index: 277