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

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

Neuron 2754 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1534242 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1511785 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1455269 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1636886 (Python Code)

Max Activating Token Index: 505

Text #4

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1569397 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1633506 (Python Code)

Max Activating Token Index: 876

Text #6

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4632. Min Act: -0.0001

Data Index: 1421653 (Python Code)

Max Activating Token Index: 112

Text #7

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1460707 (Python Code)

Max Activating Token Index: 394

Text #8

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1635960 (Python Code)

Max Activating Token Index: 356

Text #9

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1525088 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1502003 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1566698 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1522706 (Python Code)

Max Activating Token Index: 826

Text #13

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1579771 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1517390 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1533875 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1458143 (Python Code)

Max Activating Token Index: 336

Text #17

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.3910. Min Act: -0.0000

Data Index: 613709 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.3779. Min Act: -0.0000

Data Index: 210262 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1507691 (Python Code)

Max Activating Token Index: 122