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

Dataset: The Pile

Neuron 3104 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: 1.6005. Min Range: -1.6005

Max Act: 1.6005. Min Act: -0.0000

Data Index: 1463286 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2965. Min Act: -0.0000

Data Index: 873128 (The Pile)

Max Activating Token Index: 691

Text #2

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1888. Min Act: -0.0000

Data Index: 312897 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1913183 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1649392 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1370875 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1436374 (The Pile)

Max Activating Token Index: 544

Text #7

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2250. Min Act: -0.0000

Data Index: 14389 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1464939 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1376739 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1997. Min Act: -0.0000

Data Index: 645022 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1727. Min Act: -0.0000

Data Index: 1509129 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1392135 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2011. Min Act: -0.0000

Data Index: 1294261 (The Pile)

Max Activating Token Index: 855

Text #14

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1076. Min Act: -0.0000

Data Index: 624547 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.0110. Min Act: -0.0000

Data Index: 764229 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.2185. Min Act: -0.0000

Data Index: 455047 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1039. Min Act: -0.0000

Data Index: 641110 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 1.6005. Min Range: -1.6005

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1162240 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 1.6005. Min Range: -1.6005

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1527608 (The Pile)

Max Activating Token Index: 852