Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4621 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.6880. Min Act: -0.0000

Data Index: 268951 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.6259. Min Act: -0.0000

Data Index: 657035 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5943. Min Act: -0.0000

Data Index: 701723 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.6253. Min Act: -0.0000

Data Index: 162915 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.6260. Min Act: -0.0000

Data Index: 541578 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.6160. Min Act: -0.0000

Data Index: 412420 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.6041. Min Act: -0.0000

Data Index: 704345 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.6305. Min Act: -0.0000

Data Index: 153941 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.6053. Min Act: -0.0000

Data Index: 572044 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5646. Min Act: -0.0000

Data Index: 644501 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5765. Min Act: -0.0000

Data Index: 14231 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5470. Min Act: -0.0000

Data Index: 574936 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1306229 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5474. Min Act: -0.0000

Data Index: 4265 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5593. Min Act: -0.0000

Data Index: 653894 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5606. Min Act: -0.0000

Data Index: 55773 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1247619 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1023865 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5102. Min Act: -0.0000

Data Index: 486457 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.6880. Min Range: -0.6880

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1086954 (C4 (Web Text))

Max Activating Token Index: 85