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

Dataset: The Pile

Neuron 1858 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1389833 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1677884 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1432932 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2241. Min Act: -0.0000

Data Index: 107195 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1821973 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2058. Min Act: -0.0000

Data Index: 569707 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1731. Min Act: -0.0000

Data Index: 174731 (The Pile)

Max Activating Token Index: 11

Text #7

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1431724 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1915. Min Act: -0.0000

Data Index: 689616 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1926. Min Act: -0.0000

Data Index: 756954 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1888229 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1678. Min Act: -0.0000

Data Index: 870645 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1663. Min Act: -0.0000

Data Index: 706984 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1484012 (The Pile)

Max Activating Token Index: 245

Text #14

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1864133 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1839. Min Act: -0.0000

Data Index: 124765 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1445827 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1474. Min Act: -0.0000

Data Index: 667740 (The Pile)

Max Activating Token Index: 674

Text #18

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1601. Min Act: -0.0000

Data Index: 49189 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1310338 (The Pile)

Max Activating Token Index: 346