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

Dataset: The Pile

Neuron 4549 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: 0.1013. Min Range: -0.1013

Max Act: 0.0999. Min Act: 0.0000

Data Index: 485791 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1207490 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1327285 (The Pile)

Max Activating Token Index: 956

Text #3

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1633083 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0897. Min Act: -0.0000

Data Index: 845037 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0866. Min Act: -0.0000

Data Index: 578267 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0767. Min Act: -0.0000

Data Index: 1915254 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0856. Min Act: -0.0000

Data Index: 875778 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0823. Min Act: 0.0000

Data Index: 1756569 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0849. Min Act: -0.0000

Data Index: 71297 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0774. Min Act: -0.0000

Data Index: 94122 (The Pile)

Max Activating Token Index: 730

Text #11

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1259217 (The Pile)

Max Activating Token Index: 689

Text #12

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0793. Min Act: -0.0000

Data Index: 608222 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0729. Min Act: -0.0000

Data Index: 648789 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0733. Min Act: -0.0000

Data Index: 422328 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1765351 (The Pile)

Max Activating Token Index: 398

Text #16

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0680. Min Act: -0.0000

Data Index: 1387067 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0728. Min Act: -0.0000

Data Index: 846181 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0791. Min Act: -0.0000

Data Index: 57076 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0706. Min Act: -0.0000

Data Index: 539518 (The Pile)

Max Activating Token Index: 779