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

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

Neuron 511 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: 0.3211. Min Range: -0.3211

Max Act: 0.3211. Min Act: -0.0001

Data Index: 1383856 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1580389 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2509. Min Act: -0.0001

Data Index: 1456025 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2245. Min Act: -0.0001

Data Index: 1599331 (Python Code)

Max Activating Token Index: 1005

Text #4

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2240. Min Act: -0.0001

Data Index: 1395336 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1612909 (Python Code)

Max Activating Token Index: 857

Text #6

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1588588 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2029. Min Act: -0.0001

Data Index: 1595975 (Python Code)

Max Activating Token Index: 123

Text #8

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1540719 (Python Code)

Max Activating Token Index: 789

Text #9

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1873. Min Act: -0.0000

Data Index: 177993 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1639866 (Python Code)

Max Activating Token Index: 188

Text #11

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1420623 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1584. Min Act: -0.0000

Data Index: 340128 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1475261 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1614099 (Python Code)

Max Activating Token Index: 538

Text #15

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1412999 (Python Code)

Max Activating Token Index: 249

Text #16

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1596728 (Python Code)

Max Activating Token Index: 358

Text #17

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1409. Min Act: -0.0001

Data Index: 5653 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1485008 (Python Code)

Max Activating Token Index: 971

Text #19

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1462407 (Python Code)

Max Activating Token Index: 599