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

Dataset: The Pile

Neuron 4088 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.6047. Min Act: -0.0000

Data Index: 912853 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.3495. Min Act: -0.0000

Data Index: 841250 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1794930 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.2492. Min Act: -0.0000

Data Index: 1891378 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.1514. Min Act: -0.0000

Data Index: 346327 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1705607 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1058593 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.2790. Min Act: -0.0000

Data Index: 499392 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.1736. Min Act: -0.0000

Data Index: 589493 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1738753 (The Pile)

Max Activating Token Index: 724

Text #10

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1920998 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1154568 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1511654 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1019248 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1791091 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1066687 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1880696 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.0365. Min Act: -0.0000

Data Index: 940724 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1261332 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1420835 (The Pile)

Max Activating Token Index: 984