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

Dataset: The Pile

Neuron 5001 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.1852. Min Act: -0.0000

Data Index: 622765 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1722393 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1665657 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1876335 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9856. Min Act: -0.0000

Data Index: 33862 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1805517 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1267818 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1834216 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1284528 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8520. Min Act: -0.0000

Data Index: 946704 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8262. Min Act: -0.0000

Data Index: 592964 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1149402 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8643. Min Act: -0.0000

Data Index: 221717 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1084696 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1069616 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1325144 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1513327 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8355. Min Act: -0.0000

Data Index: 881072 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.7847. Min Act: -0.0000

Data Index: 3724 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8849. Min Act: -0.0000

Data Index: 771334 (The Pile)

Max Activating Token Index: 494