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

Dataset: The Pile

Neuron 139 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1175024 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2727. Min Act: -0.0000

Data Index: 385618 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1725765 (The Pile)

Max Activating Token Index: 868

Text #3

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2517. Min Act: -0.0000

Data Index: 80343 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2314. Min Act: -0.0000

Data Index: 533028 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1026276 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2469. Min Act: -0.0000

Data Index: 277294 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1193841 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1574583 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1226321 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1675354 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2272. Min Act: -0.0000

Data Index: 594726 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1833. Min Act: -0.0000

Data Index: 651070 (The Pile)

Max Activating Token Index: 792

Text #13

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2229. Min Act: -0.0000

Data Index: 356190 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2084. Min Act: -0.0000

Data Index: 769851 (The Pile)

Max Activating Token Index: 903

Text #15

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1512623 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2150. Min Act: -0.0000

Data Index: 975141 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2100. Min Act: -0.0000

Data Index: 743511 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1512666 (The Pile)

Max Activating Token Index: 31

Text #19

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1131821 (The Pile)

Max Activating Token Index: 21