Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1656 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.4354. Min Act: -0.0000

Data Index: 740495 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.4293. Min Act: -0.0000

Data Index: 207035 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.4613. Min Act: -0.0000

Data Index: 379489 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.4463. Min Act: -0.0000

Data Index: 1490840 (The Pile)

Max Activating Token Index: 727

Text #4

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1014768 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.3890. Min Act: -0.0000

Data Index: 922712 (The Pile)

Max Activating Token Index: 656

Text #6

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.3301. Min Act: -0.0000

Data Index: 166942 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1842. Min Act: -0.0000

Data Index: 1900499 (The Pile)

Max Activating Token Index: 648

Text #8

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2213. Min Act: -0.0000

Data Index: 23326 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2546. Min Act: -0.0000

Data Index: 585171 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2011. Min Act: -0.0000

Data Index: 719732 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2334. Min Act: -0.0000

Data Index: 1704368 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1964678 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1687389 (The Pile)

Max Activating Token Index: 873

Text #14

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1804. Min Act: -0.0000

Data Index: 149710 (The Pile)

Max Activating Token Index: 724

Text #15

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2092. Min Act: -0.0000

Data Index: 1426575 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1980. Min Act: -0.0000

Data Index: 1856922 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1364808 (The Pile)

Max Activating Token Index: 689

Text #18

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1555562 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.2058. Min Act: -0.0000

Data Index: 517468 (The Pile)

Max Activating Token Index: 672