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

Dataset: The Pile

Neuron 4386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2824. Min Act: -0.0000

Data Index: 619275 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1285588 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1986712 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1593606 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2320. Min Act: -0.0000

Data Index: 193910 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1694984 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2357. Min Act: -0.0000

Data Index: 513018 (The Pile)

Max Activating Token Index: 681

Text #7

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1904. Min Act: -0.0000

Data Index: 271429 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2312. Min Act: -0.0000

Data Index: 768357 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1975586 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1435288 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2019. Min Act: -0.0000

Data Index: 513513 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2126. Min Act: -0.0000

Data Index: 305609 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1554186 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1816052 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1937. Min Act: -0.0000

Data Index: 580260 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1896. Min Act: -0.0000

Data Index: 957059 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1905. Min Act: -0.0000

Data Index: 975224 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1982. Min Act: -0.0000

Data Index: 10491 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1877843 (The Pile)

Max Activating Token Index: 877