Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1758 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1547035 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2227. Min Act: -0.0000

Data Index: 668010 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2142. Min Act: -0.0000

Data Index: 104339 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1104209 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1997563 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1866405 (The Pile)

Max Activating Token Index: 859

Text #6

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1789. Min Act: -0.0000

Data Index: 7725 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1904. Min Act: -0.0000

Data Index: 738100 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1921303 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1335026 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1865. Min Act: -0.0000

Data Index: 101034 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1511. Min Act: -0.0000

Data Index: 310106 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1257245 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1187323 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1241607 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1618. Min Act: -0.0000

Data Index: 485579 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1951460 (The Pile)

Max Activating Token Index: 590

Text #17

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1678344 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1876405 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1982769 (The Pile)

Max Activating Token Index: 394