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

Dataset: The Pile

Neuron 4922 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: 0.9539. Min Range: -0.9539

Max Act: 0.8492. Min Act: -0.0000

Data Index: 325506 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8350. Min Act: -0.0000

Data Index: 124412 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1850755 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.9539. Min Act: -0.0000

Data Index: 145449 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1304251 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1902694 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6624. Min Act: -0.0000

Data Index: 896823 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8037. Min Act: -0.0000

Data Index: 473869 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1433717 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1337760 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1860972 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1907868 (The Pile)

Max Activating Token Index: 858

Text #12

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1104129 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1548217 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.5349. Min Act: -0.0000

Data Index: 708620 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6342. Min Act: -0.0000

Data Index: 801174 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.5352. Min Act: -0.0000

Data Index: 856099 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.4905. Min Act: -0.0000

Data Index: 321007 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1275538 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.5309. Min Act: -0.0000

Data Index: 137141 (The Pile)

Max Activating Token Index: 428