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

Dataset: The Pile

Neuron 1409 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: 0.1564. Min Range: -0.1564

Max Act: 0.1452. Min Act: -0.0000

Data Index: 257640 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1564. Min Act: -0.0000

Data Index: 998467 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1406622 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1948245 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1231260 (The Pile)

Max Activating Token Index: 476

Text #5

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1187. Min Act: -0.0000

Data Index: 564483 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1447803 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1344. Min Act: -0.0000

Data Index: 53662 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1338. Min Act: -0.0000

Data Index: 840372 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1301805 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1464115 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1031195 (The Pile)

Max Activating Token Index: 724

Text #12

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1057. Min Act: -0.0000

Data Index: 420991 (The Pile)

Max Activating Token Index: 271

Text #13

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1176. Min Act: -0.0000

Data Index: 335072 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1035. Min Act: -0.0000

Data Index: 9378 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1003. Min Act: -0.0000

Data Index: 299475 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1035. Min Act: -0.0000

Data Index: 797129 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1073. Min Act: -0.0000

Data Index: 508375 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.0994. Min Act: -0.0000

Data Index: 26996 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1168552 (The Pile)

Max Activating Token Index: 479