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

Dataset: The Pile

Neuron 4371 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.9267. Min Act: -0.0000

Data Index: 189029 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1037227 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1384188 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1218896 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8457. Min Act: -0.0000

Data Index: 772141 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1314041 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1209685 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1700259 (The Pile)

Max Activating Token Index: 119

Text #8

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1428114 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7435. Min Act: -0.0000

Data Index: 803866 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7107. Min Act: -0.0000

Data Index: 681758 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7354. Min Act: -0.0000

Data Index: 857158 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7974. Min Act: -0.0000

Data Index: 518432 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1960288 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1454636 (The Pile)

Max Activating Token Index: 156

Text #15

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1044259 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1460979 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1805694 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1043400 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7178. Min Act: -0.0000

Data Index: 633970 (The Pile)

Max Activating Token Index: 366