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

Dataset: The Pile

Neuron 618 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: 1.1971. Min Range: -1.1971

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1497535 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1551098 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1633890 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9256. Min Act: -0.0000

Data Index: 155891 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1624. Min Act: -0.0000

Data Index: 256233 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0521. Min Act: -0.0000

Data Index: 102510 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1282222 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0795. Min Act: -0.0000

Data Index: 529076 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9629. Min Act: -0.0000

Data Index: 54952 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1537388 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1730294 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0426. Min Act: -0.0000

Data Index: 808439 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1795303 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0404. Min Act: -0.0000

Data Index: 959827 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1867796 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1654242 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9265. Min Act: -0.0000

Data Index: 366113 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8992. Min Act: -0.0000

Data Index: 40898 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1817485 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1736506 (The Pile)

Max Activating Token Index: 423