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

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

Neuron 600 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: 0.1777. Min Range: -0.1777

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1559039 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1469. Min Act: -0.0000

Data Index: 485132 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1561133 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1602. Min Act: -0.0001

Data Index: 974422 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1652724 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1531306 (Python Code)

Max Activating Token Index: 573

Text #6

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1613279 (Python Code)

Max Activating Token Index: 625

Text #7

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1424226 (Python Code)

Max Activating Token Index: 844

Text #8

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1576189 (Python Code)

Max Activating Token Index: 546

Text #9

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1525. Min Act: -0.0001

Data Index: 239779 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1648058 (Python Code)

Max Activating Token Index: 448

Text #11

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1651268 (Python Code)

Max Activating Token Index: 699

Text #12

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1418. Min Act: -0.0001

Data Index: 177696 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1328. Min Act: -0.0001

Data Index: 468848 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1283. Min Act: -0.0001

Data Index: 173118 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1272. Min Act: -0.0000

Data Index: 593378 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1380963 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1041. Min Act: -0.0001

Data Index: 513036 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1291. Min Act: -0.0000

Data Index: 134743 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1310. Min Act: -0.0000

Data Index: 634145 (C4 (Web Text))

Max Activating Token Index: 925