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

Dataset: The Pile

Neuron 4689 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1098353 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1313056 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1873996 (The Pile)

Max Activating Token Index: 17

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0711. Min Act: -0.0001

Data Index: 722644 (The Pile)

Max Activating Token Index: 17

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1503406 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1967741 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1272396 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1625730 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0591. Min Act: -0.0000

Data Index: 120284 (The Pile)

Max Activating Token Index: 846

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1761017 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0586. Min Act: -0.0000

Data Index: 474963 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1578684 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1218455 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1627664 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0511. Min Act: -0.0000

Data Index: 548381 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1278393 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0537. Min Act: -0.0000

Data Index: 361274 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1135797 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1580748 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1472508 (The Pile)

Max Activating Token Index: 526