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

Dataset: The Pile

Neuron 4767 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.9748. Min Act: -0.0000

Data Index: 439591 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.9691. Min Act: -0.0000

Data Index: 1638585 (The Pile)

Max Activating Token Index: 763

Text #2

Max Range: 5.1220. Min Range: -5.1220

Max Act: 5.1220. Min Act: -0.0000

Data Index: 682139 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.4812. Min Act: -0.0000

Data Index: 1709644 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.4078. Min Act: 0.0000

Data Index: 1115216 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.2424. Min Act: -0.0000

Data Index: 1124714 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.1967. Min Act: -0.0000

Data Index: 1213508 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.1536. Min Act: -0.0000

Data Index: 287013 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.9825. Min Act: -0.0000

Data Index: 1398188 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.3105. Min Act: -0.0000

Data Index: 1465701 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.6315. Min Act: -0.0000

Data Index: 276012 (The Pile)

Max Activating Token Index: 482

Text #11

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.6603. Min Act: -0.0000

Data Index: 1499434 (The Pile)

Max Activating Token Index: 512

Text #12

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.6093. Min Act: -0.0000

Data Index: 1122387 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.4315. Min Act: -0.0000

Data Index: 107545 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.2391. Min Act: -0.0000

Data Index: 1464126 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.8509. Min Act: -0.0000

Data Index: 457376 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.3982. Min Act: -0.0000

Data Index: 1826022 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 5.1220. Min Range: -5.1220

Max Act: 2.9221. Min Act: -0.0000

Data Index: 1622476 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.5280. Min Act: -0.0000

Data Index: 99182 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 5.1220. Min Range: -5.1220

Max Act: 3.3671. Min Act: -0.0000

Data Index: 1080878 (The Pile)

Max Activating Token Index: 308