Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1076825 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2030. Min Act: -0.0000

Data Index: 634738 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1952. Min Act: -0.0000

Data Index: 822913 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1644457 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1890. Min Act: -0.0000

Data Index: 289904 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1721126 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1796. Min Act: -0.0001

Data Index: 631726 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1818906 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1890. Min Act: -0.0000

Data Index: 549096 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1808. Min Act: -0.0000

Data Index: 698964 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1708. Min Act: -0.0001

Data Index: 1053551 (The Pile)

Max Activating Token Index: 904

Text #11

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1038205 (The Pile)

Max Activating Token Index: 881

Text #12

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1801485 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1816820 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1365456 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1613. Min Act: -0.0000

Data Index: 825923 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1352867 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1015213 (The Pile)

Max Activating Token Index: 956

Text #18

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1426086 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1212391 (The Pile)

Max Activating Token Index: 914