Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1956 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1930771 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1891381 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.2555. Min Act: -0.0000

Data Index: 850145 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1700958 (The Pile)

Max Activating Token Index: 804

Text #4

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.2433. Min Act: -0.0000

Data Index: 458862 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.2082. Min Act: -0.0000

Data Index: 487110 (The Pile)

Max Activating Token Index: 867

Text #6

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.2052. Min Act: -0.0000

Data Index: 654637 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.2104. Min Act: -0.0000

Data Index: 747129 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.2046. Min Act: -0.0000

Data Index: 539702 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1965327 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1940. Min Act: -0.0000

Data Index: 208245 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1914. Min Act: -0.0000

Data Index: 8844 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1890. Min Act: -0.0000

Data Index: 531096 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1393230 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1206718 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1931. Min Act: -0.0000

Data Index: 961065 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1385268 (The Pile)

Max Activating Token Index: 750

Text #17

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1806. Min Act: -0.0000

Data Index: 747210 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1730. Min Act: -0.0000

Data Index: 867278 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.2768. Min Range: -0.2768

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1625110 (The Pile)

Max Activating Token Index: 540