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

Dataset: The Pile

Neuron 4949 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: 0.3941. Min Range: -0.3941

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1570318 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1606289 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1815503 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1830421 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1254730 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2127. Min Act: -0.0000

Data Index: 450048 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2031. Min Act: -0.0000

Data Index: 397038 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2071. Min Act: -0.0000

Data Index: 51970 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1798737 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1906137 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1881. Min Act: -0.0000

Data Index: 196441 (The Pile)

Max Activating Token Index: 30

Text #11

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1916. Min Act: -0.0000

Data Index: 967914 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1171635 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1883. Min Act: -0.0000

Data Index: 96275 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1940. Min Act: -0.0000

Data Index: 109948 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1702832 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1579532 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1977. Min Act: -0.0000

Data Index: 205093 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1842. Min Act: -0.0000

Data Index: 196464 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 0.3941. Min Range: -0.3941

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1305576 (The Pile)

Max Activating Token Index: 387