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

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

Neuron 101 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: 0.8162. Min Range: -0.8162

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1526420 (Python Code)

Max Activating Token Index: 131

Text #1

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1456990 (Python Code)

Max Activating Token Index: 233

Text #2

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1472330 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1513974 (Python Code)

Max Activating Token Index: 965

Text #4

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1412993 (Python Code)

Max Activating Token Index: 285

Text #5

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1455540 (Python Code)

Max Activating Token Index: 565

Text #6

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1650174 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1414528 (Python Code)

Max Activating Token Index: 506

Text #8

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1436087 (Python Code)

Max Activating Token Index: 733

Text #9

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1443137 (Python Code)

Max Activating Token Index: 908

Text #10

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1437674 (Python Code)

Max Activating Token Index: 527

Text #11

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1428799 (Python Code)

Max Activating Token Index: 406

Text #12

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1628147 (Python Code)

Max Activating Token Index: 463

Text #13

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1547838 (Python Code)

Max Activating Token Index: 528

Text #14

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1506630 (Python Code)

Max Activating Token Index: 928

Text #15

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1441519 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1370402 (Python Code)

Max Activating Token Index: 489

Text #17

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1366899 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1415897 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1433649 (Python Code)

Max Activating Token Index: 355