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

Dataset: The Pile

Neuron 1355 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.9770. Min Act: -0.0000

Data Index: 849855 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 1.0561. Min Range: -1.0561

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1803824 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8915. Min Act: -0.0000

Data Index: 487623 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8618. Min Act: -0.0000

Data Index: 291673 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1833018 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1838984 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8019. Min Act: -0.0000

Data Index: 148728 (The Pile)

Max Activating Token Index: 787

Text #7

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1094184 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1672542 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8496. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8965. Min Act: -0.0000

Data Index: 725013 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1841386 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8183. Min Act: -0.0000

Data Index: 67114 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.7361. Min Act: -0.0000

Data Index: 546714 (The Pile)

Max Activating Token Index: 899

Text #14

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8687. Min Act: -0.0000

Data Index: 542294 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1399521 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1381142 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8955. Min Act: 0.0003

Data Index: 1833167 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8152. Min Act: -0.0000

Data Index: 99393 (The Pile)

Max Activating Token Index: 530

Text #19

Max Range: 1.0561. Min Range: -1.0561

Max Act: 0.8257. Min Act: -0.0000

Data Index: 736356 (The Pile)

Max Activating Token Index: 676