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

Dataset: The Pile

Neuron 928 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.6370. Min Act: -0.0000

Data Index: 768129 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1807770 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4803. Min Act: -0.0000

Data Index: 290122 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.3322. Min Act: -0.0000

Data Index: 1042435 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.3497. Min Act: -0.0000

Data Index: 290661 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.3383. Min Act: -0.0000

Data Index: 65642 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.3412. Min Act: -0.0000

Data Index: 459826 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.2553. Min Act: -0.0000

Data Index: 328068 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.1969. Min Act: -0.0000

Data Index: 569677 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.1410. Min Act: -0.0000

Data Index: 383786 (The Pile)

Max Activating Token Index: 762

Text #10

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1395376 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.0870. Min Act: -0.0000

Data Index: 1138894 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1838159 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.1697. Min Act: -0.0000

Data Index: 170778 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.0036. Min Act: -0.0000

Data Index: 1641139 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1015460 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1412307 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.0354. Min Act: -0.0000

Data Index: 928426 (The Pile)

Max Activating Token Index: 363

Text #18

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1667259 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.0588. Min Act: -0.0000

Data Index: 269625 (The Pile)

Max Activating Token Index: 635