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

Dataset: The Pile

Neuron 2573 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1894. Min Range: -4.1894

Max Act: 4.1894. Min Act: -0.0000

Data Index: 1751123 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.6177. Min Act: -0.0000

Data Index: 1264672 (The Pile)

Max Activating Token Index: 450

Text #2

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.4437. Min Act: -0.0000

Data Index: 1133844 (The Pile)

Max Activating Token Index: 524

Text #3

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.4290. Min Act: -0.0000

Data Index: 1843427 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.4159. Min Act: -0.0000

Data Index: 1161066 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.2753. Min Act: -0.0000

Data Index: 837804 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.3171. Min Act: -0.0000

Data Index: 595035 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.2907. Min Act: -0.0000

Data Index: 395754 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.3097. Min Act: -0.0000

Data Index: 47106 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.3094. Min Act: -0.0000

Data Index: 1765395 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.2729. Min Act: -0.0000

Data Index: 1091552 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.4180. Min Act: -0.0000

Data Index: 1300484 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.1158. Min Act: -0.0000

Data Index: 79005 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.2472. Min Act: -0.0000

Data Index: 1163899 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.2597. Min Act: -0.0000

Data Index: 1060159 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.2282. Min Act: -0.0000

Data Index: 385615 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.2093. Min Act: -0.0000

Data Index: 1435646 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.2226. Min Act: -0.0000

Data Index: 589833 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 4.1894. Min Range: -4.1894

Max Act: 2.9104. Min Act: -0.0000

Data Index: 1414861 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 4.1894. Min Range: -4.1894

Max Act: 3.0517. Min Act: -0.0000

Data Index: 1607637 (The Pile)

Max Activating Token Index: 312