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

Dataset: The Pile

Neuron 1952 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: 1.6031. Min Range: -1.6031

Max Act: 1.6031. Min Act: -0.0000

Data Index: 1496054 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.4279. Min Act: -0.0000

Data Index: 774875 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.2636. Min Act: -0.0000

Data Index: 719832 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1690362 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.3390. Min Act: -0.0000

Data Index: 1588449 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.2837. Min Act: -0.0000

Data Index: 1666656 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.2612. Min Act: -0.0000

Data Index: 1499019 (The Pile)

Max Activating Token Index: 366

Text #7

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.2567. Min Act: -0.0000

Data Index: 1580989 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.2517. Min Act: -0.0000

Data Index: 1383377 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.2276. Min Act: -0.0000

Data Index: 1740756 (The Pile)

Max Activating Token Index: 504

Text #10

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0173. Min Act: -0.0000

Data Index: 865000 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.1029. Min Act: -0.0001

Data Index: 443227 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1816283 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1486902 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1256993 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.1566. Min Act: -0.0000

Data Index: 1041528 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1068370 (The Pile)

Max Activating Token Index: 629

Text #17

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.1299. Min Act: -0.0000

Data Index: 383577 (The Pile)

Max Activating Token Index: 968

Text #18

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.0933. Min Act: -0.0000

Data Index: 304585 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 1.6031. Min Range: -1.6031

Max Act: 1.1160. Min Act: -0.0000

Data Index: 772967 (The Pile)

Max Activating Token Index: 65