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

Dataset: The Pile

Neuron 477 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: 0.8274. Min Range: -0.8274

Max Act: 0.8274. Min Act: -0.0000

Data Index: 635849 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1873197 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6864. Min Act: -0.0000

Data Index: 127472 (The Pile)

Max Activating Token Index: 1019

Text #3

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1823324 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6948. Min Act: -0.0000

Data Index: 175590 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1478938 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1677121 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1514348 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.4888. Min Act: -0.0000

Data Index: 698958 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1616932 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5804. Min Act: -0.0000

Data Index: 501935 (The Pile)

Max Activating Token Index: 434

Text #11

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1878205 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1506839 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1430356 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1121484 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1109559 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5269. Min Act: -0.0000

Data Index: 383816 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1325372 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5765. Min Act: -0.0000

Data Index: 229848 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5264. Min Act: -0.0000

Data Index: 907711 (The Pile)

Max Activating Token Index: 399