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

Dataset: The Pile

Neuron 4176 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1133412 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6490. Min Act: -0.0000

Data Index: 507861 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6400. Min Act: -0.0000

Data Index: 347067 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5501. Min Act: -0.0000

Data Index: 582673 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.4564. Min Act: -0.0000

Data Index: 539660 (The Pile)

Max Activating Token Index: 253

Text #5

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.4396. Min Act: -0.0000

Data Index: 784176 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.4279. Min Act: -0.0000

Data Index: 467418 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.4453. Min Act: -0.0000

Data Index: 11324 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1815105 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3677. Min Act: -0.0000

Data Index: 198002 (The Pile)

Max Activating Token Index: 824

Text #10

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3531. Min Act: -0.0000

Data Index: 407099 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3505. Min Act: -0.0000

Data Index: 904231 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1851841 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1011554 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1464008 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3066. Min Act: -0.0000

Data Index: 271787 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3049. Min Act: -0.0000

Data Index: 32913 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1820357 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1082066 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.2785. Min Act: -0.0000

Data Index: 142286 (The Pile)

Max Activating Token Index: 1014