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

Dataset: The Pile

Neuron 1765 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: 1.3616. Min Range: -1.3616

Max Act: 1.3616. Min Act: -0.0000

Data Index: 702948 (The Pile)

Max Activating Token Index: 543

Text #1

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.3132. Min Act: -0.0000

Data Index: 930818 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1061533 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.2898. Min Act: -0.0000

Data Index: 38226 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.2870. Min Act: -0.0000

Data Index: 692647 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.2119. Min Act: -0.0000

Data Index: 293887 (The Pile)

Max Activating Token Index: 946

Text #6

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.2365. Min Act: -0.0000

Data Index: 1000792 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.2081. Min Act: -0.0000

Data Index: 1423160 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1870. Min Act: -0.0000

Data Index: 604854 (The Pile)

Max Activating Token Index: 249

Text #9

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1926803 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.2264. Min Act: -0.0000

Data Index: 505709 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1786. Min Act: -0.0000

Data Index: 811400 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1115728 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1559. Min Act: -0.0000

Data Index: 1407985 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1357123 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1713. Min Act: -0.0000

Data Index: 984541 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1836. Min Act: -0.0000

Data Index: 499275 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1208377 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1682. Min Act: -0.0000

Data Index: 489635 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1413. Min Act: -0.0000

Data Index: 15415 (The Pile)

Max Activating Token Index: 887