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

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

Neuron 3946 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3963. Min Act: -0.0001

Data Index: 1369283 (Python Code)

Max Activating Token Index: 970

Text #1

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1591021 (Python Code)

Max Activating Token Index: 789

Text #2

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.4098. Min Act: -0.0001

Data Index: 1428818 (Python Code)

Max Activating Token Index: 905

Text #3

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1592441 (Python Code)

Max Activating Token Index: 464

Text #4

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1643467 (Python Code)

Max Activating Token Index: 923

Text #5

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1560023 (Python Code)

Max Activating Token Index: 308

Text #6

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3930. Min Act: -0.0001

Data Index: 1521336 (Python Code)

Max Activating Token Index: 947

Text #7

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3971. Min Act: -0.0001

Data Index: 1461897 (Python Code)

Max Activating Token Index: 717

Text #8

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3821. Min Act: -0.0001

Data Index: 1388573 (Python Code)

Max Activating Token Index: 572

Text #9

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.4200. Min Act: -0.0001

Data Index: 1515372 (Python Code)

Max Activating Token Index: 709

Text #10

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3695. Min Act: -0.0001

Data Index: 1517835 (Python Code)

Max Activating Token Index: 256

Text #11

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3676. Min Act: -0.0001

Data Index: 1510929 (Python Code)

Max Activating Token Index: 357

Text #12

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3767. Min Act: -0.0001

Data Index: 1402485 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3780. Min Act: -0.0001

Data Index: 1529545 (Python Code)

Max Activating Token Index: 380

Text #14

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3883. Min Act: -0.0001

Data Index: 1634490 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1614927 (Python Code)

Max Activating Token Index: 349

Text #16

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3642. Min Act: -0.0001

Data Index: 1365385 (Python Code)

Max Activating Token Index: 680

Text #17

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3882. Min Act: -0.0001

Data Index: 1577041 (Python Code)

Max Activating Token Index: 687

Text #18

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3866. Min Act: -0.0001

Data Index: 1455127 (Python Code)

Max Activating Token Index: 264

Text #19

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3764. Min Act: -0.0001

Data Index: 1557324 (Python Code)

Max Activating Token Index: 902