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

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

Neuron 1788 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.2377. Min Act: -0.0000

Data Index: 859206 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.1627. Min Act: -0.0000

Data Index: 461553 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1333998 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1352290 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9962. Min Act: -0.0000

Data Index: 682338 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9946. Min Act: -0.0000

Data Index: 546350 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9890. Min Act: -0.0000

Data Index: 12771 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.1080. Min Act: -0.0000

Data Index: 943278 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9657. Min Act: -0.0000

Data Index: 74401 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.0007. Min Act: -0.0000

Data Index: 667307 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.0366. Min Act: -0.0000

Data Index: 707139 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9745. Min Act: -0.0000

Data Index: 278289 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1044321 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1276733 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.0013. Min Act: -0.0000

Data Index: 488996 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9031. Min Act: -0.0000

Data Index: 715002 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8968. Min Act: -0.0000

Data Index: 171957 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8875. Min Act: -0.0000

Data Index: 484470 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8825. Min Act: -0.0000

Data Index: 697226 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1076307 (C4 (Web Text))

Max Activating Token Index: 798