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

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

Neuron 2721 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.6378. Min Act: -0.0000

Data Index: 1130683 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.3127. Min Act: -0.0000

Data Index: 466265 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.1783. Min Act: -0.0000

Data Index: 401500 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1139556 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.1093. Min Act: -0.0000

Data Index: 122306 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1377062 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1557416 (Python Code)

Max Activating Token Index: 910

Text #7

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.0361. Min Act: -0.0000

Data Index: 496162 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.9920. Min Act: -0.0000

Data Index: 432382 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1634282 (Python Code)

Max Activating Token Index: 489

Text #10

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.9514. Min Act: -0.0000

Data Index: 280775 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1152701 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.9886. Min Act: -0.0000

Data Index: 97331 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1385155 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1115861 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1309441 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1638766 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1559916 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.8726. Min Act: -0.0000

Data Index: 184078 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.6378. Min Range: -1.6378

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1506079 (Python Code)

Max Activating Token Index: 428