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

Dataset: The Pile

Neuron 5076 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.7452. Min Act: -0.0000

Data Index: 32887 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.9839. Min Act: -0.0000

Data Index: 1694543 (The Pile)

Max Activating Token Index: 39

Text #2

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8462. Min Act: -0.0000

Data Index: 1899155 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.6938. Min Act: -0.0000

Data Index: 380836 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8034. Min Act: -0.0000

Data Index: 159156 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.6398. Min Act: -0.0000

Data Index: 176998 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.4550. Min Act: -0.0000

Data Index: 67465 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.5625. Min Act: -0.0000

Data Index: 1455140 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.6789. Min Act: -0.0000

Data Index: 1773403 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.2861. Min Act: -0.0000

Data Index: 598464 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.2345. Min Act: 0.0000

Data Index: 615016 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.3676. Min Act: -0.0000

Data Index: 1950096 (The Pile)

Max Activating Token Index: 771

Text #12

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.1885. Min Act: -0.0000

Data Index: 1463039 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.2844. Min Act: -0.0000

Data Index: 222420 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.4447. Min Act: -0.0000

Data Index: 1536316 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.2519. Min Act: -0.0000

Data Index: 1361763 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 3.9839. Min Range: -3.9839

Max Act: 2.9502. Min Act: -0.0000

Data Index: 54663 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.3996. Min Act: -0.0000

Data Index: 928760 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.0792. Min Act: -0.0000

Data Index: 504195 (The Pile)

Max Activating Token Index: 278

Text #19

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.0653. Min Act: -0.0000

Data Index: 1792748 (The Pile)

Max Activating Token Index: 28