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

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

Neuron 1463 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: 1.9089. Min Range: -1.9089

Max Act: 1.9089. Min Act: -0.0000

Data Index: 184104 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.7806. Min Act: -0.0000

Data Index: 550880 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.6260. Min Act: -0.0000

Data Index: 910358 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.6631. Min Act: -0.0000

Data Index: 1086712 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.3995. Min Act: -0.0000

Data Index: 414588 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.3638. Min Act: -0.0000

Data Index: 1315083 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1118448 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.3392. Min Act: -0.0000

Data Index: 1034628 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1036060 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.1275. Min Act: -0.0000

Data Index: 1148280 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.1796. Min Act: -0.0000

Data Index: 799823 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.1938. Min Act: -0.0000

Data Index: 587753 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.0944. Min Act: -0.0000

Data Index: 575398 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.2132. Min Act: -0.0000

Data Index: 785183 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.1399. Min Act: -0.0000

Data Index: 953653 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.1378. Min Act: -0.0000

Data Index: 621537 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.1253. Min Act: -0.0000

Data Index: 74843 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1096295 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.1082. Min Act: -0.0000

Data Index: 198466 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.1024. Min Act: -0.0000

Data Index: 934152 (C4 (Web Text))

Max Activating Token Index: 533