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

Dataset: The Pile

Neuron 16 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1471. Min Act: 0.0000

Data Index: 1023790 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1376. Min Act: 0.0000

Data Index: 753465 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1272. Min Act: 0.0000

Data Index: 990952 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1241. Min Act: 0.0000

Data Index: 740250 (The Pile)

Max Activating Token Index: 602

Text #4

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1174. Min Act: 0.0000

Data Index: 492850 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1123. Min Act: 0.0000

Data Index: 712233 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1096. Min Act: 0.0000

Data Index: 1386751 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1094. Min Act: 0.0000

Data Index: 158450 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1069. Min Act: 0.0000

Data Index: 1036467 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1057. Min Act: 0.0000

Data Index: 1066791 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1053. Min Act: 0.0000

Data Index: 1786248 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1093. Min Act: 0.0000

Data Index: 1174290 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1072. Min Act: 0.0000

Data Index: 1384717 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1057. Min Act: 0.0000

Data Index: 309624 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1021. Min Act: 0.0000

Data Index: 1247791 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1019. Min Act: 0.0000

Data Index: 388853 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1020. Min Act: 0.0000

Data Index: 1276434 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1048. Min Act: 0.0000

Data Index: 320619 (The Pile)

Max Activating Token Index: 47

Text #18

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1011. Min Act: 0.0000

Data Index: 1353012 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1006. Min Act: 0.0000

Data Index: 572029 (The Pile)

Max Activating Token Index: 30