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

Dataset: The Pile

Neuron 2376 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: 0.8013. Min Range: -0.8013

Max Act: 0.7929. Min Act: -0.0000

Data Index: 641004 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1228850 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1786551 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1162695 (The Pile)

Max Activating Token Index: 421

Text #4

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.7164. Min Act: -0.0000

Data Index: 365671 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5970. Min Act: -0.0000

Data Index: 194276 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1361431 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1691906 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5893. Min Act: -0.0000

Data Index: 353273 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5612. Min Act: -0.0000

Data Index: 840741 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5963. Min Act: -0.0001

Data Index: 1229383 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5339. Min Act: -0.0000

Data Index: 74306 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6327. Min Act: -0.0000

Data Index: 256187 (The Pile)

Max Activating Token Index: 556

Text #13

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1626006 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.6110. Min Act: -0.0000

Data Index: 332009 (The Pile)

Max Activating Token Index: 455

Text #15

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5997. Min Act: -0.0000

Data Index: 20328 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1900369 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5218. Min Act: -0.0000

Data Index: 707205 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1215142 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 0.8013. Min Range: -0.8013

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1106450 (The Pile)

Max Activating Token Index: 147