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

Dataset: The Pile

Neuron 1509 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.6480. Min Act: -0.0000

Data Index: 616564 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1693156 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.4013. Min Act: -0.0000

Data Index: 455005 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.3060. Min Act: -0.0000

Data Index: 643272 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.3054. Min Act: -0.0000

Data Index: 834151 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1648728 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2442. Min Act: -0.0000

Data Index: 571132 (The Pile)

Max Activating Token Index: 635

Text #7

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.3168. Min Act: -0.0000

Data Index: 280502 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2776. Min Act: -0.0000

Data Index: 716817 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1213452 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.3054. Min Act: -0.0000

Data Index: 74528 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1663662 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1088341 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1020349 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1959880 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1274080 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1748760 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2544. Min Act: -0.0000

Data Index: 468361 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1260076 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 0.6480. Min Range: -0.6480

Max Act: 0.2525. Min Act: -0.0000

Data Index: 22720 (The Pile)

Max Activating Token Index: 945