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

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

Neuron 2575 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.2784. Min Act: -0.0000

Data Index: 1514439 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.1919. Min Act: -0.0000

Data Index: 1556350 (Python Code)

Max Activating Token Index: 982

Text #2

Max Range: 1.2784. Min Range: -1.2784

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1446587 (Python Code)

Max Activating Token Index: 842

Text #3

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1641767 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1636548 (Python Code)

Max Activating Token Index: 558

Text #5

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1395475 (Python Code)

Max Activating Token Index: 100

Text #6

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1529876 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1378156 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1451260 (Python Code)

Max Activating Token Index: 841

Text #9

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1637062 (Python Code)

Max Activating Token Index: 173

Text #10

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1471919 (Python Code)

Max Activating Token Index: 765

Text #11

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1466455 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1364213 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1617698 (Python Code)

Max Activating Token Index: 550

Text #14

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1459168 (Python Code)

Max Activating Token Index: 59

Text #15

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1634600 (Python Code)

Max Activating Token Index: 547

Text #16

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1517393 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1519781 (Python Code)

Max Activating Token Index: 878

Text #18

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1637395 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 1.2784. Min Range: -1.2784

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1587043 (Python Code)

Max Activating Token Index: 816