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

Dataset: The Pile

Neuron 683 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: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1301422 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1529487 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1732311 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2012. Min Act: -0.0000

Data Index: 505267 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1705795 (The Pile)

Max Activating Token Index: 727

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1092219 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1011335 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2085. Min Act: -0.0000

Data Index: 606526 (The Pile)

Max Activating Token Index: 627

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1033643 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1769388 (The Pile)

Max Activating Token Index: 409

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2051. Min Act: -0.0000

Data Index: 591679 (The Pile)

Max Activating Token Index: 719

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1665059 (The Pile)

Max Activating Token Index: 606

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1282064 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1864215 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1762544 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1014180 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1815. Min Act: -0.0000

Data Index: 911770 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1860. Min Act: -0.0000

Data Index: 751351 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1790. Min Act: -0.0000

Data Index: 143380 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1970885 (The Pile)

Max Activating Token Index: 507