Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2756 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0591. Min Act: -0.0004

Data Index: 1656498 (Python Code)

Max Activating Token Index: 510

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0556. Min Act: -0.0004

Data Index: 1562349 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0599. Min Act: -0.0004

Data Index: 1623930 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0004

Data Index: 1515224 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0567. Min Act: -0.0004

Data Index: 1621668 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0584. Min Act: -0.0004

Data Index: 1608100 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0560. Min Act: -0.0004

Data Index: 1391001 (Python Code)

Max Activating Token Index: 260

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0563. Min Act: -0.0004

Data Index: 1568912 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0581. Min Act: -0.0004

Data Index: 1455411 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0580. Min Act: -0.0004

Data Index: 1396248 (Python Code)

Max Activating Token Index: 587

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0552. Min Act: -0.0004

Data Index: 1626930 (Python Code)

Max Activating Token Index: 505

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0529. Min Act: -0.0004

Data Index: 1382640 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0570. Min Act: -0.0004

Data Index: 1372267 (Python Code)

Max Activating Token Index: 695

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0521. Min Act: -0.0004

Data Index: 1643651 (Python Code)

Max Activating Token Index: 532

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0537. Min Act: -0.0004

Data Index: 1561272 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0560. Min Act: -0.0004

Data Index: 1607663 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0515. Min Act: -0.0004

Data Index: 1499938 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0534. Min Act: -0.0004

Data Index: 1509363 (Python Code)

Max Activating Token Index: 275

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0511. Min Act: -0.0004

Data Index: 1387524 (Python Code)

Max Activating Token Index: 672

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0528. Min Act: -0.0004

Data Index: 1429264 (Python Code)

Max Activating Token Index: 587