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

Dataset: The Pile

Neuron 4602 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: 0.1799. Min Range: -0.1799

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1475795 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1610. Min Act: -0.0000

Data Index: 742219 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1509. Min Act: -0.0000

Data Index: 179473 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1394855 (The Pile)

Max Activating Token Index: 691

Text #4

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1759327 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1399. Min Act: -0.0000

Data Index: 191906 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1019863 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1375. Min Act: -0.0000

Data Index: 591809 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1926593 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1195073 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1200. Min Act: -0.0000

Data Index: 599673 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1229. Min Act: -0.0000

Data Index: 727132 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1179. Min Act: -0.0000

Data Index: 914567 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1630265 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1513932 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1216. Min Act: -0.0000

Data Index: 262634 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1186. Min Act: -0.0000

Data Index: 422548 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1033096 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1815845 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1177. Min Act: -0.0000

Data Index: 96430 (The Pile)

Max Activating Token Index: 90