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

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

Neuron 3242 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1389019 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.7116. Min Act: -0.0000

Data Index: 1428715 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.7123. Min Act: -0.0000

Data Index: 1489908 (Python Code)

Max Activating Token Index: 427

Text #3

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.6010. Min Act: -0.0000

Data Index: 1456688 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5668. Min Act: -0.0000

Data Index: 1416728 (Python Code)

Max Activating Token Index: 509

Text #5

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.6497. Min Act: -0.0000

Data Index: 1428827 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5014. Min Act: -0.0000

Data Index: 1512340 (Python Code)

Max Activating Token Index: 605

Text #7

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4708. Min Act: -0.0000

Data Index: 1374548 (Python Code)

Max Activating Token Index: 508

Text #8

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4229. Min Act: -0.0000

Data Index: 1586745 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1521154 (Python Code)

Max Activating Token Index: 345

Text #10

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4935. Min Act: -0.0000

Data Index: 1642479 (Python Code)

Max Activating Token Index: 396

Text #11

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1454844 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3732. Min Act: -0.0000

Data Index: 1571727 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3575. Min Act: -0.0000

Data Index: 1398993 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3486. Min Act: -0.0000

Data Index: 1516080 (Python Code)

Max Activating Token Index: 806

Text #15

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3894. Min Act: -0.0000

Data Index: 1427257 (Python Code)

Max Activating Token Index: 443

Text #16

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4483. Min Act: -0.0000

Data Index: 1399306 (Python Code)

Max Activating Token Index: 781

Text #17

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1575357 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.4349. Min Act: -0.0000

Data Index: 1470107 (Python Code)

Max Activating Token Index: 243

Text #19

Max Range: 1.7123. Min Range: -1.7123

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1524929 (Python Code)

Max Activating Token Index: 431