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

Dataset: The Pile

Neuron 2148 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1489500 (The Pile)

Max Activating Token Index: 186

Text #1

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2396. Min Act: -0.0000

Data Index: 821241 (The Pile)

Max Activating Token Index: 763

Text #2

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1601715 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1437583 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1217956 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1199879 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1856. Min Act: 0.0000

Data Index: 238607 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1733. Min Act: -0.0000

Data Index: 798353 (The Pile)

Max Activating Token Index: 113

Text #8

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1108059 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1946. Min Act: -0.0000

Data Index: 785293 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1812. Min Act: 0.0000

Data Index: 250166 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1881. Min Act: 0.0000

Data Index: 734354 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1891. Min Act: -0.0000

Data Index: 705697 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1954692 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1285373 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1310908 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1795. Min Act: -0.0000

Data Index: 44136 (The Pile)

Max Activating Token Index: 532

Text #17

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1304434 (The Pile)

Max Activating Token Index: 289

Text #18

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1640. Min Act: 0.0000

Data Index: 1314984 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1864207 (The Pile)

Max Activating Token Index: 959