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

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

Neuron 2217 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1469154 (Python Code)

Max Activating Token Index: 633

Text #1

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.5770. Min Act: -0.0000

Data Index: 103741 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1647984 (Python Code)

Max Activating Token Index: 651

Text #3

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4953. Min Act: -0.0000

Data Index: 550951 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1591584 (Python Code)

Max Activating Token Index: 614

Text #5

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1274197 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1426924 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4323. Min Act: -0.0000

Data Index: 183541 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1374890 (Python Code)

Max Activating Token Index: 770

Text #9

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3633. Min Act: -0.0001

Data Index: 1398878 (Python Code)

Max Activating Token Index: 626

Text #10

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1541909 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1436255 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1620727 (Python Code)

Max Activating Token Index: 94

Text #13

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3777. Min Act: -0.0000

Data Index: 995391 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1498120 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3904. Min Act: 0.0000

Data Index: 1247381 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1462553 (Python Code)

Max Activating Token Index: 557

Text #17

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1368649 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1645817 (Python Code)

Max Activating Token Index: 682

Text #19

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1447610 (Python Code)

Max Activating Token Index: 402