Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2453 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.4325. Min Act: -0.0000

Data Index: 481904 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.4117. Min Act: -0.0000

Data Index: 708299 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.4035. Min Act: -0.0000

Data Index: 988062 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.4200. Min Act: -0.0000

Data Index: 166232 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3780. Min Act: -0.0000

Data Index: 217391 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1302115 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1179559 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1295122 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3468. Min Act: -0.0000

Data Index: 233031 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3550. Min Act: -0.0000

Data Index: 98469 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3508. Min Act: -0.0000

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3217. Min Act: -0.0000

Data Index: 867066 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3386. Min Act: -0.0000

Data Index: 496797 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1087940 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3179. Min Act: -0.0000

Data Index: 884326 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3442. Min Act: -0.0000

Data Index: 433012 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3279. Min Act: -0.0000

Data Index: 219396 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1253786 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1310843 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1267693 (C4 (Web Text))

Max Activating Token Index: 459