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

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

Neuron 4781 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: 0.2028. Min Range: -0.2028

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1551863 (Python Code)

Max Activating Token Index: 245

Text #1

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1182700 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1546603 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1521455 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1380964 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1702. Min Act: -0.0001

Data Index: 227319 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1451220 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1578. Min Act: -0.0000

Data Index: 207756 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1538000 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1406755 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1697. Min Act: -0.0001

Data Index: 1500994 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1461002 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1463325 (Python Code)

Max Activating Token Index: 652

Text #13

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1512. Min Act: -0.0000

Data Index: 238758 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1395157 (Python Code)

Max Activating Token Index: 68

Text #15

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1388. Min Act: -0.0000

Data Index: 142348 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1366755 (Python Code)

Max Activating Token Index: 225

Text #17

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1478361 (Python Code)

Max Activating Token Index: 438

Text #18

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1445911 (Python Code)

Max Activating Token Index: 948

Text #19

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1371316 (Python Code)

Max Activating Token Index: 876