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

Dataset: The Pile

Neuron 492 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: 0.2704. Min Range: -0.2704

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1368817 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2559. Min Act: -0.0000

Data Index: 332670 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2565. Min Act: -0.0000

Data Index: 973023 (The Pile)

Max Activating Token Index: 32

Text #3

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2522. Min Act: -0.0000

Data Index: 770863 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1754219 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1166480 (The Pile)

Max Activating Token Index: 11

Text #6

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2332. Min Act: -0.0000

Data Index: 979975 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2246. Min Act: -0.0000

Data Index: 219388 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1222306 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1983264 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1426459 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2171. Min Act: -0.0000

Data Index: 708149 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2181. Min Act: -0.0000

Data Index: 841509 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1164683 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1831312 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1488803 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1965. Min Act: -0.0000

Data Index: 569502 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1980. Min Act: -0.0000

Data Index: 694097 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1965. Min Act: -0.0000

Data Index: 170018 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1756624 (The Pile)

Max Activating Token Index: 11