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

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

Neuron 2981 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.2882. Min Act: -0.0000

Data Index: 1436486 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.4507. Min Act: -0.0000

Data Index: 441517 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.2882. Min Act: -0.0000

Data Index: 1503627 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.3485. Min Act: -0.0000

Data Index: 1548533 (Python Code)

Max Activating Token Index: 781

Text #4

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.4746. Min Act: -0.0000

Data Index: 916544 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.4628. Min Act: -0.0000

Data Index: 1409815 (Python Code)

Max Activating Token Index: 957

Text #6

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.3143. Min Act: -0.0000

Data Index: 1583780 (Python Code)

Max Activating Token Index: 30

Text #7

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.3142. Min Act: -0.0000

Data Index: 1458017 (Python Code)

Max Activating Token Index: 55

Text #8

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.2950. Min Act: -0.0000

Data Index: 1466027 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.2783. Min Act: -0.0000

Data Index: 1504167 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.1351. Min Act: -0.0000

Data Index: 1237479 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.0957. Min Act: -0.0000

Data Index: 1124446 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.2175. Min Act: -0.0000

Data Index: 3698 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.1834. Min Act: -0.0000

Data Index: 1323729 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.1736. Min Act: -0.0000

Data Index: 1518379 (Python Code)

Max Activating Token Index: 46

Text #15

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.0500. Min Act: -0.0000

Data Index: 1606922 (Python Code)

Max Activating Token Index: 858

Text #16

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.1650. Min Act: -0.0000

Data Index: 1641644 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.0431. Min Act: -0.0000

Data Index: 1515163 (Python Code)

Max Activating Token Index: 517

Text #18

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.1396. Min Act: -0.0000

Data Index: 1655201 (Python Code)

Max Activating Token Index: 867

Text #19

Max Range: 2.4746. Min Range: -2.4746

Max Act: 2.1419. Min Act: -0.0000

Data Index: 89081 (C4 (Web Text))

Max Activating Token Index: 685