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

Dataset: The Pile

Neuron 2465 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: 3.6817. Min Range: -3.6817

Max Act: 3.6817. Min Act: -0.0000

Data Index: 96027 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.1558. Min Act: -0.0000

Data Index: 1358693 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.9434. Min Act: -0.0000

Data Index: 1298346 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.6736. Min Act: -0.0000

Data Index: 1357184 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.9225. Min Act: -0.0000

Data Index: 1730697 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.8603. Min Act: -0.0000

Data Index: 1702472 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.7461. Min Act: -0.0000

Data Index: 1007151 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.6931. Min Act: -0.0000

Data Index: 916116 (The Pile)

Max Activating Token Index: 413

Text #8

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.5234. Min Act: -0.0000

Data Index: 589068 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.6563. Min Act: -0.0000

Data Index: 1413458 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.5071. Min Act: -0.0000

Data Index: 1364864 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.3592. Min Act: -0.0000

Data Index: 1301456 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.9342. Min Act: -0.0000

Data Index: 936175 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.4652. Min Act: -0.0000

Data Index: 964100 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.4362. Min Act: -0.0000

Data Index: 340360 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.4147. Min Act: -0.0000

Data Index: 26626 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.3798. Min Act: -0.0000

Data Index: 1281199 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.3796. Min Act: -0.0000

Data Index: 1703601 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.3723. Min Act: -0.0000

Data Index: 1777682 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.2396. Min Act: -0.0000

Data Index: 567212 (The Pile)

Max Activating Token Index: 489