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

Dataset: The Pile

Neuron 547 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: 0.3045. Min Range: -0.3045

Max Act: 0.3045. Min Act: -0.0000

Data Index: 89072 (The Pile)

Max Activating Token Index: 868

Text #1

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1854551 (The Pile)

Max Activating Token Index: 1005

Text #2

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1381911 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1859015 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2508. Min Act: -0.0000

Data Index: 726466 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1902283 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1233593 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2669. Min Act: -0.0000

Data Index: 518360 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1781683 (The Pile)

Max Activating Token Index: 298

Text #9

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1266976 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2253. Min Act: -0.0000

Data Index: 650246 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2326. Min Act: -0.0000

Data Index: 574837 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1279578 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1276904 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1219961 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1957595 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2115. Min Act: -0.0000

Data Index: 500319 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2260. Min Act: -0.0000

Data Index: 3141 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2391. Min Act: -0.0000

Data Index: 313240 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2365. Min Act: -0.0000

Data Index: 189934 (The Pile)

Max Activating Token Index: 547