Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3035 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2281. Min Act: -0.0000

Data Index: 548493 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1104200 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2062. Min Act: -0.0000

Data Index: 544500 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1131478 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1305368 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1420871 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1384289 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1825. Min Act: -0.0000

Data Index: 276336 (The Pile)

Max Activating Token Index: 718

Text #8

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1882. Min Act: -0.0000

Data Index: 780786 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1745759 (The Pile)

Max Activating Token Index: 860

Text #10

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1822. Min Act: -0.0000

Data Index: 506377 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1743. Min Act: -0.0000

Data Index: 260355 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1777. Min Act: -0.0000

Data Index: 512448 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1866. Min Act: -0.0001

Data Index: 1561480 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1946113 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1746. Min Act: -0.0000

Data Index: 754634 (The Pile)

Max Activating Token Index: 452

Text #16

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1746. Min Act: -0.0000

Data Index: 590548 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1369761 (The Pile)

Max Activating Token Index: 492

Text #18

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1798. Min Act: -0.0000

Data Index: 823558 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 0.2281. Min Range: -0.2281

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1649165 (The Pile)

Max Activating Token Index: 131