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

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

Neuron 4489 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.7821. Min Act: -0.0000

Data Index: 1417682 (Python Code)

Max Activating Token Index: 1021

Text #1

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.8734. Min Act: -0.0000

Data Index: 1612622 (Python Code)

Max Activating Token Index: 296

Text #2

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.6762. Min Act: -0.0000

Data Index: 1589679 (Python Code)

Max Activating Token Index: 391

Text #3

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.5969. Min Act: -0.0000

Data Index: 1474717 (Python Code)

Max Activating Token Index: 368

Text #4

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.7911. Min Act: -0.0000

Data Index: 1453715 (Python Code)

Max Activating Token Index: 872

Text #5

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.4039. Min Act: -0.0000

Data Index: 1571562 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.3119. Min Act: -0.0000

Data Index: 1371310 (Python Code)

Max Activating Token Index: 488

Text #7

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.3940. Min Act: -0.0000

Data Index: 1608509 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2735. Min Act: -0.0000

Data Index: 1399791 (Python Code)

Max Activating Token Index: 671

Text #9

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2298. Min Act: -0.0000

Data Index: 1503525 (Python Code)

Max Activating Token Index: 966

Text #10

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.3384. Min Act: -0.0000

Data Index: 1467761 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.1020. Min Act: -0.0000

Data Index: 1528242 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2304. Min Act: -0.0000

Data Index: 1486157 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.3400. Min Act: -0.0000

Data Index: 1401708 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 2.8734. Min Range: -2.8734

Max Act: 1.9380. Min Act: -0.0000

Data Index: 1432771 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.0548. Min Act: -0.0000

Data Index: 1599918 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2887. Min Act: -0.0000

Data Index: 1574290 (Python Code)

Max Activating Token Index: 787

Text #17

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.0202. Min Act: -0.0000

Data Index: 1372485 (Python Code)

Max Activating Token Index: 679

Text #18

Max Range: 2.8734. Min Range: -2.8734

Max Act: 1.9921. Min Act: -0.0000

Data Index: 159135 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 2.8734. Min Range: -2.8734

Max Act: 1.8543. Min Act: -0.0000

Data Index: 1640654 (Python Code)

Max Activating Token Index: 633