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

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

Neuron 4092 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.7078. Min Act: -0.0000

Data Index: 1271150 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 4.7078. Min Range: -4.7078

Max Act: 4.1444. Min Act: -0.0000

Data Index: 512504 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.9294. Min Act: -0.0000

Data Index: 649381 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.7553. Min Act: -0.0000

Data Index: 1000198 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.7233. Min Act: -0.0000

Data Index: 1071048 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.3006. Min Act: -0.0000

Data Index: 963286 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.4038. Min Act: -0.0000

Data Index: 298243 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.4868. Min Act: -0.0000

Data Index: 901454 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.3317. Min Act: -0.0000

Data Index: 757642 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.3006. Min Act: -0.0000

Data Index: 604849 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.2677. Min Act: -0.0000

Data Index: 1252400 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 4.7078. Min Range: -4.7078

Max Act: 2.9755. Min Act: -0.0000

Data Index: 987863 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.4072. Min Act: -0.0000

Data Index: 448175 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.2260. Min Act: -0.0000

Data Index: 423319 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.2228. Min Act: -0.0000

Data Index: 792841 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.3909. Min Act: -0.0000

Data Index: 140637 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.2015. Min Act: -0.0000

Data Index: 617869 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.1781. Min Act: -0.0000

Data Index: 1321753 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.1692. Min Act: -0.0000

Data Index: 910237 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 4.7078. Min Range: -4.7078

Max Act: 3.0148. Min Act: -0.0000

Data Index: 535209 (C4 (Web Text))

Max Activating Token Index: 618