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

Dataset: The Pile

Neuron 4248 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: 0.7987. Min Range: -0.7987

Max Act: 0.7987. Min Act: -0.0000

Data Index: 982985 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.7850. Min Act: -0.0000

Data Index: 676338 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1856101 (The Pile)

Max Activating Token Index: 95

Text #3

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1836803 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.7287. Min Act: -0.0000

Data Index: 776973 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1270198 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.7023. Min Act: -0.0000

Data Index: 552750 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1424151 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1647838 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1594035 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1462305 (The Pile)

Max Activating Token Index: 583

Text #11

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1177698 (The Pile)

Max Activating Token Index: 24

Text #12

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1645667 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6633. Min Act: -0.0000

Data Index: 188558 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6563. Min Act: -0.0000

Data Index: 348660 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6432. Min Act: -0.0000

Data Index: 582295 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6476. Min Act: -0.0000

Data Index: 430343 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6699. Min Act: -0.0000

Data Index: 683538 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1206414 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6375. Min Act: -0.0000

Data Index: 622406 (The Pile)

Max Activating Token Index: 547