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

Dataset: The Pile

Neuron 3334 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: 0.2304. Min Range: -0.2304

Max Act: 0.2304. Min Act: -0.0000

Data Index: 793895 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2062. Min Act: -0.0000

Data Index: 593178 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1246309 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.2141. Min Act: -0.0000

Data Index: 891891 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1227084 (The Pile)

Max Activating Token Index: 958

Text #5

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1849. Min Act: -0.0000

Data Index: 341551 (The Pile)

Max Activating Token Index: 899

Text #6

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1438722 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1798. Min Act: -0.0000

Data Index: 299235 (The Pile)

Max Activating Token Index: 861

Text #8

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1697859 (The Pile)

Max Activating Token Index: 579

Text #9

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1074689 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1018724 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1803429 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1828. Min Act: -0.0000

Data Index: 791443 (The Pile)

Max Activating Token Index: 672

Text #13

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1029852 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1595. Min Act: -0.0000

Data Index: 23802 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1854824 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1348967 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1489. Min Act: -0.0000

Data Index: 25173 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1599. Min Act: -0.0000

Data Index: 228362 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 0.2304. Min Range: -0.2304

Max Act: 0.1590. Min Act: -0.0000

Data Index: 544984 (The Pile)

Max Activating Token Index: 834