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

Dataset: The Pile

Neuron 3444 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1051277 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1450. Min Act: -0.0000

Data Index: 260288 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1281. Min Act: -0.0000

Data Index: 877232 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1279. Min Act: -0.0000

Data Index: 207676 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1139. Min Act: -0.0000

Data Index: 375820 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1496692 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1212. Min Act: -0.0000

Data Index: 716553 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1110. Min Act: -0.0000

Data Index: 885060 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1007. Min Act: -0.0000

Data Index: 899947 (The Pile)

Max Activating Token Index: 681

Text #9

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1055. Min Act: -0.0000

Data Index: 854273 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1019. Min Act: -0.0000

Data Index: 667311 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1384555 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1673007 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1030. Min Act: -0.0000

Data Index: 244087 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0939. Min Act: -0.0000

Data Index: 260621 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1232625 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1233851 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1193645 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0989. Min Act: -0.0000

Data Index: 418176 (The Pile)

Max Activating Token Index: 265

Text #19

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1646203 (The Pile)

Max Activating Token Index: 651