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

Dataset: The Pile

Neuron 2020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2116. Min Range: -1.2116

Max Act: 1.2116. Min Act: -0.0000

Data Index: 926811 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 1.2116. Min Range: -1.2116

Max Act: 1.0773. Min Act: -0.0000

Data Index: 768547 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9646. Min Act: -0.0000

Data Index: 520449 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1502654 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1986842 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1547139 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1781092 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.8792. Min Act: -0.0000

Data Index: 758791 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1014018 (The Pile)

Max Activating Token Index: 818

Text #9

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1903057 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1893373 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1015485 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.7866. Min Act: -0.0000

Data Index: 344558 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1034889 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.8299. Min Act: -0.0000

Data Index: 862946 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.7964. Min Act: -0.0000

Data Index: 140255 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1236983 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.7406. Min Act: -0.0000

Data Index: 866852 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1802402 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 1.2116. Min Range: -1.2116

Max Act: 0.7789. Min Act: -0.0000

Data Index: 200209 (The Pile)

Max Activating Token Index: 746