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

Dataset: The Pile

Neuron 2885 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2401. Min Act: -0.0000

Data Index: 258153 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2098. Min Act: -0.0000

Data Index: 362600 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1451527 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1110500 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1945. Min Act: -0.0000

Data Index: 865369 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1288226 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1572859 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1607. Min Act: -0.0000

Data Index: 681605 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1561. Min Act: -0.0000

Data Index: 347979 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1320204 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1082468 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1455. Min Act: -0.0000

Data Index: 815755 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1454. Min Act: -0.0000

Data Index: 366405 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1410332 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1305255 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1430. Min Act: -0.0000

Data Index: 763997 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1130596 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1384. Min Act: -0.0000

Data Index: 620704 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1697213 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1768032 (The Pile)

Max Activating Token Index: 761