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

Dataset: The Pile

Neuron 2302 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: 1.1890. Min Range: -1.1890

Max Act: 1.1890. Min Act: -0.0000

Data Index: 973413 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1589347 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1055815 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0573. Min Act: -0.0000

Data Index: 505226 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1327294 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0103. Min Act: -0.0000

Data Index: 131453 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1425717 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1931817 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1704034 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1475517 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1157425 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1712854 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1094236 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8302. Min Act: -0.0000

Data Index: 989323 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8516. Min Act: -0.0000

Data Index: 485198 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8478. Min Act: -0.0000

Data Index: 1335817 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1459889 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1135194 (The Pile)

Max Activating Token Index: 383

Text #18

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1911828 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1799544 (The Pile)

Max Activating Token Index: 27