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

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

Neuron 4503 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: 2.6784. Min Range: -2.6784

Max Act: 2.2953. Min Act: -0.0000

Data Index: 1452400 (Python Code)

Max Activating Token Index: 801

Text #1

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.6784. Min Act: -0.0000

Data Index: 1467832 (Python Code)

Max Activating Token Index: 397

Text #2

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.4955. Min Act: -0.0000

Data Index: 1407386 (Python Code)

Max Activating Token Index: 1010

Text #3

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.2820. Min Act: -0.0000

Data Index: 1551003 (Python Code)

Max Activating Token Index: 621

Text #4

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.4031. Min Act: -0.0000

Data Index: 1426485 (Python Code)

Max Activating Token Index: 470

Text #5

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.2730. Min Act: -0.0001

Data Index: 1612863 (Python Code)

Max Activating Token Index: 477

Text #6

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.2997. Min Act: -0.0001

Data Index: 1367291 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.0853. Min Act: -0.0000

Data Index: 1631860 (Python Code)

Max Activating Token Index: 605

Text #8

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.2402. Min Act: -0.0000

Data Index: 1601592 (Python Code)

Max Activating Token Index: 963

Text #9

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3629. Min Act: -0.0000

Data Index: 1579830 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.1562. Min Act: -0.0001

Data Index: 1473014 (Python Code)

Max Activating Token Index: 368

Text #11

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.0311. Min Act: -0.0000

Data Index: 1408766 (Python Code)

Max Activating Token Index: 938

Text #12

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.0575. Min Act: -0.0000

Data Index: 1545531 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.0338. Min Act: -0.0000

Data Index: 1608172 (Python Code)

Max Activating Token Index: 528

Text #14

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.1427. Min Act: -0.0000

Data Index: 1416486 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 2.6784. Min Range: -2.6784

Max Act: 1.8122. Min Act: -0.0000

Data Index: 1566705 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 2.6784. Min Range: -2.6784

Max Act: 1.8522. Min Act: -0.0001

Data Index: 1385897 (Python Code)

Max Activating Token Index: 578

Text #17

Max Range: 2.6784. Min Range: -2.6784

Max Act: 1.9100. Min Act: -0.0000

Data Index: 1620825 (Python Code)

Max Activating Token Index: 701

Text #18

Max Range: 2.6784. Min Range: -2.6784

Max Act: 1.7125. Min Act: -0.0000

Data Index: 1585032 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 2.6784. Min Range: -2.6784

Max Act: 1.8067. Min Act: -0.0000

Data Index: 1547660 (Python Code)

Max Activating Token Index: 317