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

Dataset: The Pile

Neuron 3768 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: 1.2424. Min Range: -1.2424

Max Act: 1.1266. Min Act: -0.0000

Data Index: 747216 (The Pile)

Max Activating Token Index: 816

Text #1

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1025493 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.2424. Min Range: -1.2424

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1029736 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1743082 (The Pile)

Max Activating Token Index: 811

Text #4

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1779. Min Act: -0.0000

Data Index: 479082 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1216924 (The Pile)

Max Activating Token Index: 502

Text #6

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1624532 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.2424. Min Act: -0.0000

Data Index: 1042282 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1650. Min Act: -0.0000

Data Index: 736103 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0816. Min Act: -0.0000

Data Index: 387549 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1066650 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1954326 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1168719 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1683802 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0142. Min Act: -0.0000

Data Index: 797801 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1910868 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0434. Min Act: -0.0000

Data Index: 967292 (The Pile)

Max Activating Token Index: 260

Text #17

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1848018 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 1.2424. Min Range: -1.2424

Max Act: 1.1159. Min Act: -0.0000

Data Index: 557938 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 1.2424. Min Range: -1.2424

Max Act: 0.9731. Min Act: -0.0000

Data Index: 540718 (The Pile)

Max Activating Token Index: 467