Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2260 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1603149 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6253. Min Act: -0.0000

Data Index: 12246 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6387. Min Act: -0.0000

Data Index: 139159 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1981921 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5159. Min Act: -0.0000

Data Index: 844375 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1277108 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1369312 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1459674 (The Pile)

Max Activating Token Index: 648

Text #8

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1664204 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1035725 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1286148 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4648. Min Act: -0.0000

Data Index: 464639 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4591. Min Act: -0.0000

Data Index: 969919 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1195122 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1547976 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1814779 (The Pile)

Max Activating Token Index: 484

Text #16

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1138701 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4016. Min Act: -0.0000

Data Index: 186675 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1513814 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1129631 (The Pile)

Max Activating Token Index: 63