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

Dataset: The Pile

Neuron 4535 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.5427. Min Act: -0.0000

Data Index: 868030 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.5258. Min Act: -0.0000

Data Index: 562025 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.5140. Min Act: 0.0000

Data Index: 1694902 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1615633 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4631. Min Act: -0.0000

Data Index: 899837 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1338259 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4436. Min Act: -0.0000

Data Index: 629494 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4427. Min Act: -0.0000

Data Index: 673880 (The Pile)

Max Activating Token Index: 423

Text #8

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1710789 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4421. Min Act: 0.0000

Data Index: 948378 (The Pile)

Max Activating Token Index: 450

Text #10

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1075177 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4102. Min Act: 0.0000

Data Index: 511199 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1041463 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1787800 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1121937 (The Pile)

Max Activating Token Index: 810

Text #15

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1457431 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4274. Min Act: -0.0000

Data Index: 957119 (The Pile)

Max Activating Token Index: 26

Text #17

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4275. Min Act: -0.0000

Data Index: 477888 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4104. Min Act: -0.0000

Data Index: 856218 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4094. Min Act: 0.0000

Data Index: 1239296 (The Pile)

Max Activating Token Index: 429