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

Dataset: The Pile

Neuron 4187 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1116667 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1256732 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1641147 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7379. Min Act: -0.0000

Data Index: 440726 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6557. Min Act: -0.0000

Data Index: 500270 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6842. Min Act: -0.0000

Data Index: 924262 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.5577. Min Act: -0.0000

Data Index: 116375 (The Pile)

Max Activating Token Index: 711

Text #7

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1028805 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7069. Min Act: -0.0000

Data Index: 203364 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6642. Min Act: -0.0000

Data Index: 455628 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6521. Min Act: -0.0000

Data Index: 170248 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6830. Min Act: -0.0000

Data Index: 551005 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1820369 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1610085 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6956. Min Act: -0.0000

Data Index: 917693 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1465743 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1367281 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1819617 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.5765. Min Act: -0.0000

Data Index: 107102 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6037. Min Act: -0.0000

Data Index: 219041 (The Pile)

Max Activating Token Index: 503