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

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

Neuron 633 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5884. Min Range: -2.5884

Max Act: 2.5884. Min Act: -0.0000

Data Index: 1613007 (Python Code)

Max Activating Token Index: 406

Text #1

Max Range: 2.5884. Min Range: -2.5884

Max Act: 2.5229. Min Act: -0.0000

Data Index: 1518711 (Python Code)

Max Activating Token Index: 913

Text #2

Max Range: 2.5884. Min Range: -2.5884

Max Act: 2.3840. Min Act: -0.0000

Data Index: 1607493 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 2.5884. Min Range: -2.5884

Max Act: 2.1283. Min Act: -0.0000

Data Index: 1369019 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.9622. Min Act: -0.0000

Data Index: 1448868 (Python Code)

Max Activating Token Index: 48

Text #5

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.9306. Min Act: -0.0000

Data Index: 1398421 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1511691 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.7306. Min Act: -0.0000

Data Index: 1510079 (Python Code)

Max Activating Token Index: 267

Text #8

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1633794 (Python Code)

Max Activating Token Index: 1013

Text #9

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1502313 (Python Code)

Max Activating Token Index: 627

Text #10

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.7670. Min Act: 0.0000

Data Index: 1551947 (Python Code)

Max Activating Token Index: 665

Text #11

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1545032 (Python Code)

Max Activating Token Index: 104

Text #12

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1634701 (Python Code)

Max Activating Token Index: 797

Text #13

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.7541. Min Act: -0.0000

Data Index: 1593344 (Python Code)

Max Activating Token Index: 555

Text #14

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.7232. Min Act: -0.0000

Data Index: 1582080 (Python Code)

Max Activating Token Index: 557

Text #15

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.7095. Min Act: -0.0000

Data Index: 1549281 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1412829 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.8474. Min Act: -0.0000

Data Index: 1654162 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.7410. Min Act: -0.0000

Data Index: 1533215 (Python Code)

Max Activating Token Index: 897

Text #19

Max Range: 2.5884. Min Range: -2.5884

Max Act: 1.6526. Min Act: -0.0000

Data Index: 1615499 (Python Code)

Max Activating Token Index: 309