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

Dataset: The Pile

Neuron 951 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: 1.3981. Min Range: -1.3981

Max Act: 1.3981. Min Act: -0.0000

Data Index: 1038856 (The Pile)

Max Activating Token Index: 813

Text #1

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1184995 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.1653. Min Act: -0.0000

Data Index: 414326 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0112. Min Act: -0.0000

Data Index: 337572 (The Pile)

Max Activating Token Index: 635

Text #4

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.1230. Min Act: -0.0000

Data Index: 178393 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0875. Min Act: -0.0000

Data Index: 573543 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.8484. Min Act: -0.0000

Data Index: 92590 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1493078 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.8504. Min Act: -0.0000

Data Index: 227388 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9563. Min Act: -0.0000

Data Index: 414084 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.8825. Min Act: -0.0000

Data Index: 511256 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1771810 (The Pile)

Max Activating Token Index: 585

Text #12

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1873201 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1325306 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1955491 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.8055. Min Act: -0.0000

Data Index: 554574 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9017. Min Act: -0.0000

Data Index: 738632 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.8918. Min Act: -0.0000

Data Index: 351264 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1244146 (The Pile)

Max Activating Token Index: 437

Text #19

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9647. Min Act: -0.0000

Data Index: 201185 (The Pile)

Max Activating Token Index: 789