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

Dataset: The Pile

Neuron 3813 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1701258 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.1358. Min Act: -0.0000

Data Index: 548008 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1970304 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1271942 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9542. Min Act: -0.0000

Data Index: 765705 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1907289 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9025. Min Act: -0.0000

Data Index: 471492 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1616292 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8428. Min Act: -0.0000

Data Index: 480108 (The Pile)

Max Activating Token Index: 730

Text #9

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9452. Min Act: -0.0001

Data Index: 1921446 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8600. Min Act: -0.0000

Data Index: 992885 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7838. Min Act: -0.0000

Data Index: 474311 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8580. Min Act: -0.0000

Data Index: 743014 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1357482 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1565021 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1882367 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7729. Min Act: -0.0000

Data Index: 42032 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7738. Min Act: -0.0000

Data Index: 824876 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1620849 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8450. Min Act: -0.0000

Data Index: 262842 (The Pile)

Max Activating Token Index: 33