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

Dataset: The Pile

Neuron 3013 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1891683 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3159. Min Act: -0.0000

Data Index: 375005 (The Pile)

Max Activating Token Index: 374

Text #2

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1562149 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.2349. Min Act: -0.0000

Data Index: 289543 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1156525 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1948. Min Act: -0.0000

Data Index: 92114 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1936. Min Act: -0.0000

Data Index: 2622 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1276062 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1142606 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1768. Min Act: -0.0000

Data Index: 162687 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1576338 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1825. Min Act: -0.0000

Data Index: 449395 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1871. Min Act: -0.0000

Data Index: 342107 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1860. Min Act: -0.0000

Data Index: 656910 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1557. Min Act: -0.0000

Data Index: 142991 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1394470 (The Pile)

Max Activating Token Index: 787

Text #16

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1378964 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1490098 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1517872 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1254960 (The Pile)

Max Activating Token Index: 350