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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4573 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1832. Min Act: -0.0000

Data Index: 698525 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1114582 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1190142 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1359269 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1213. Min Act: -0.0000

Data Index: 5099 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1255. Min Act: -0.0000

Data Index: 307194 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1142. Min Act: -0.0000

Data Index: 122751 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1548697 (Python Code)

Max Activating Token Index: 494

Text #8

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1188229 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1417757 (Python Code)

Max Activating Token Index: 1018

Text #10

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1017. Min Act: -0.0000

Data Index: 519956 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1365972 (Python Code)

Max Activating Token Index: 830

Text #12

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1405879 (Python Code)

Max Activating Token Index: 575

Text #13

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1033. Min Act: -0.0000

Data Index: 802022 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1378223 (Python Code)

Max Activating Token Index: 943

Text #15

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1582428 (Python Code)

Max Activating Token Index: 992

Text #16

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1258529 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1627905 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1614400 (Python Code)

Max Activating Token Index: 680

Text #19

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1418527 (Python Code)

Max Activating Token Index: 993