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

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

Neuron 5843 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.2390. Min Act: -0.0000

Data Index: 353099 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 1.2390. Min Range: -1.2390

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1233047 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.8681. Min Act: 0.0000

Data Index: 988797 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.8588. Min Act: 0.0000

Data Index: 507826 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.8022. Min Act: -0.0000

Data Index: 290944 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1092895 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.7314. Min Act: -0.0000

Data Index: 783209 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.7282. Min Act: -0.0000

Data Index: 51369 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.7209. Min Act: 0.0000

Data Index: 1283116 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.6884. Min Act: 0.0001

Data Index: 672790 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.6806. Min Act: 0.0000

Data Index: 1310104 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.6508. Min Act: -0.0000

Data Index: 337548 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1273625 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.6581. Min Act: -0.0000

Data Index: 600446 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.7010. Min Act: 0.0000

Data Index: 974148 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.6715. Min Act: -0.0000

Data Index: 283567 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.6128. Min Act: -0.0000

Data Index: 167154 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.5822. Min Act: 0.0001

Data Index: 397608 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.6229. Min Act: 0.0001

Data Index: 73815 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 1.2390. Min Range: -1.2390

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1347294 (C4 (Web Text))

Max Activating Token Index: 304