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

Dataset: The Pile

Neuron 585 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: 0.7300. Min Range: -0.7300

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1796599 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1004920 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4810. Min Act: -0.0000

Data Index: 983630 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4623. Min Act: -0.0000

Data Index: 465422 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1274687 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4120. Min Act: -0.0000

Data Index: 948859 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4295. Min Act: -0.0000

Data Index: 725177 (The Pile)

Max Activating Token Index: 797

Text #7

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4384. Min Act: -0.0000

Data Index: 992491 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4173. Min Act: -0.0000

Data Index: 775337 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1216194 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1449062 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1742576 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3718. Min Act: -0.0000

Data Index: 987629 (The Pile)

Max Activating Token Index: 920

Text #13

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1470420 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1861298 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3512. Min Act: -0.0000

Data Index: 303036 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3948. Min Act: -0.0000

Data Index: 759782 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3510. Min Act: -0.0000

Data Index: 128255 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3356. Min Act: -0.0000

Data Index: 84657 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3355. Min Act: -0.0000

Data Index: 797710 (The Pile)

Max Activating Token Index: 447