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

Dataset: The Pile

Neuron 3312 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.2003. Min Act: -0.0000

Data Index: 70555 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.2022. Min Act: -0.0000

Data Index: 385944 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.2230. Min Act: -0.0000

Data Index: 724330 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.2275. Min Act: -0.0000

Data Index: 167829 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1660. Min Act: -0.0000

Data Index: 556388 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1869. Min Act: -0.0000

Data Index: 54117 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1572. Min Act: -0.0000

Data Index: 549324 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1331242 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1885687 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1805. Min Act: -0.0000

Data Index: 141517 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1065261 (The Pile)

Max Activating Token Index: 376

Text #11

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1836. Min Act: -0.0000

Data Index: 497134 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1735039 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1458. Min Act: -0.0000

Data Index: 488151 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1675. Min Act: -0.0000

Data Index: 248220 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1236396 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1377161 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1688622 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1947771 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1568. Min Act: -0.0000

Data Index: 316937 (The Pile)

Max Activating Token Index: 167