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

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

Neuron 4945 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.5860. Min Act: -0.0001

Data Index: 1619816 (Python Code)

Max Activating Token Index: 252

Text #1

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.5323. Min Act: -0.0000

Data Index: 1619376 (Python Code)

Max Activating Token Index: 815

Text #2

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.4193. Min Act: -0.0000

Data Index: 1550800 (Python Code)

Max Activating Token Index: 427

Text #3

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.3950. Min Act: -0.0000

Data Index: 1425941 (Python Code)

Max Activating Token Index: 853

Text #4

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.3098. Min Act: -0.0001

Data Index: 1586596 (Python Code)

Max Activating Token Index: 725

Text #5

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.3559. Min Act: -0.0000

Data Index: 1578032 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.2834. Min Act: -0.0000

Data Index: 1405180 (Python Code)

Max Activating Token Index: 779

Text #7

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.2381. Min Act: -0.0001

Data Index: 1388340 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9974. Min Act: -0.0000

Data Index: 1631687 (Python Code)

Max Activating Token Index: 651

Text #9

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.1980. Min Act: -0.0001

Data Index: 1610785 (Python Code)

Max Activating Token Index: 812

Text #10

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9711. Min Act: -0.0000

Data Index: 1504604 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.0733. Min Act: -0.0000

Data Index: 1413771 (Python Code)

Max Activating Token Index: 730

Text #12

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9400. Min Act: -0.0000

Data Index: 1452602 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9141. Min Act: -0.0001

Data Index: 1369443 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.0188. Min Act: -0.0000

Data Index: 1548521 (Python Code)

Max Activating Token Index: 535

Text #15

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.0986. Min Act: -0.0001

Data Index: 1399184 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9888. Min Act: -0.0000

Data Index: 1599812 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9535. Min Act: -0.0000

Data Index: 1362344 (Python Code)

Max Activating Token Index: 989

Text #18

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9175. Min Act: -0.0001

Data Index: 1555410 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.0221. Min Act: -0.0000

Data Index: 1482923 (Python Code)

Max Activating Token Index: 709