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

Dataset: The Pile

Neuron 2092 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: 0.9309. Min Range: -0.9309

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1513082 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.8560. Min Act: -0.0000

Data Index: 593803 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.8008. Min Act: -0.0000

Data Index: 447567 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7039. Min Act: -0.0000

Data Index: 817482 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7222. Min Act: -0.0000

Data Index: 21520 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7096. Min Act: -0.0000

Data Index: 773994 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7068. Min Act: -0.0000

Data Index: 408546 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1797443 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1381817 (The Pile)

Max Activating Token Index: 908

Text #9

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.6413. Min Act: -0.0000

Data Index: 385759 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1485857 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1874352 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.6240. Min Act: -0.0000

Data Index: 949146 (The Pile)

Max Activating Token Index: 623

Text #13

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.5998. Min Act: -0.0000

Data Index: 926378 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1675617 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1070494 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1303890 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.5744. Min Act: -0.0000

Data Index: 202175 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1053575 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1835807 (The Pile)

Max Activating Token Index: 911