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

Dataset: The Pile

Neuron 3852 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: 0.2811. Min Range: -0.2811

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1277252 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2634. Min Act: -0.0000

Data Index: 326818 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1615603 (The Pile)

Max Activating Token Index: 72

Text #3

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2387. Min Act: -0.0000

Data Index: 230347 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2360. Min Act: -0.0000

Data Index: 786011 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2518. Min Act: -0.0000

Data Index: 195342 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2271. Min Act: -0.0000

Data Index: 219086 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1952265 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1974970 (The Pile)

Max Activating Token Index: 183

Text #9

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2371. Min Act: -0.0000

Data Index: 914552 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1330703 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2433. Min Act: -0.0000

Data Index: 21302 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2121. Min Act: -0.0000

Data Index: 723411 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1012505 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1666834 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2188. Min Act: -0.0000

Data Index: 912242 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1580678 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1608519 (The Pile)

Max Activating Token Index: 216

Text #18

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2000. Min Act: -0.0000

Data Index: 985331 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1590414 (The Pile)

Max Activating Token Index: 171