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

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

Neuron 4497 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: 1.6128. Min Range: -1.6128

Max Act: 1.5244. Min Act: -0.0000

Data Index: 774364 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.6128. Min Act: -0.0000

Data Index: 523546 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.4876. Min Act: -0.0000

Data Index: 387747 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.4787. Min Act: -0.0000

Data Index: 60340 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.4329. Min Act: -0.0000

Data Index: 765093 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.4002. Min Act: -0.0000

Data Index: 370174 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1245497 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.1823. Min Act: -0.0000

Data Index: 915389 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1283963 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.2142. Min Act: -0.0000

Data Index: 313638 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1034188 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.1360. Min Act: -0.0000

Data Index: 133502 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.1212. Min Act: -0.0000

Data Index: 359833 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1329771 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1202732 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.1352. Min Act: -0.0000

Data Index: 724893 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.1133. Min Act: -0.0000

Data Index: 679501 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1306304 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.0959. Min Act: -0.0000

Data Index: 796584 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 1.6128. Min Range: -1.6128

Max Act: 1.0847. Min Act: -0.0000

Data Index: 255981 (C4 (Web Text))

Max Activating Token Index: 513