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

Dataset: The Pile

Neuron 3951 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: 0.5421. Min Range: -0.5421

Max Act: 0.5408. Min Act: -0.0000

Data Index: 567841 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1658817 (The Pile)

Max Activating Token Index: 203

Text #2

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.5421. Min Act: -0.0000

Data Index: 912137 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1230943 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4531. Min Act: -0.0000

Data Index: 812418 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1417778 (The Pile)

Max Activating Token Index: 587

Text #6

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1684868 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1782894 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1608151 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1337263 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4185. Min Act: -0.0000

Data Index: 682806 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1440265 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1445568 (The Pile)

Max Activating Token Index: 920

Text #13

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1911911 (The Pile)

Max Activating Token Index: 511

Text #14

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1505346 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3887. Min Act: -0.0000

Data Index: 669045 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4011. Min Act: -0.0000

Data Index: 109923 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4027. Min Act: -0.0000

Data Index: 707134 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3819. Min Act: -0.0000

Data Index: 983561 (The Pile)

Max Activating Token Index: 720

Text #19

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1693507 (The Pile)

Max Activating Token Index: 634