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

Dataset: The Pile

Neuron 2393 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: 0.2634. Min Range: -0.2634

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1814215 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2491. Min Act: -0.0000

Data Index: 210198 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1201315 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1169648 (The Pile)

Max Activating Token Index: 921

Text #4

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1957. Min Act: -0.0000

Data Index: 602064 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1884792 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1934384 (The Pile)

Max Activating Token Index: 102

Text #7

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1366115 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1995. Min Act: -0.0000

Data Index: 451522 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1991. Min Act: -0.0000

Data Index: 967057 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1841. Min Act: -0.0000

Data Index: 14803 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1993205 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1772. Min Act: -0.0000

Data Index: 263516 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1338704 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1605. Min Act: -0.0000

Data Index: 952101 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1679. Min Act: -0.0000

Data Index: 709062 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2132. Min Act: -0.0000

Data Index: 719769 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1865. Min Act: -0.0000

Data Index: 55116 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1792. Min Act: -0.0000

Data Index: 114697 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1990456 (The Pile)

Max Activating Token Index: 837