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

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

Neuron 3781 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.2262. Min Act: -0.0000

Data Index: 276109 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1917. Min Act: -0.0000

Data Index: 512825 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1775. Min Act: -0.0000

Data Index: 536602 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1147606 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1664. Min Act: -0.0000

Data Index: 981858 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1665. Min Act: -0.0000

Data Index: 288280 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1537924 (Python Code)

Max Activating Token Index: 512

Text #7

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1613. Min Act: -0.0000

Data Index: 167742 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1609. Min Act: -0.0000

Data Index: 590871 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1332162 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1599. Min Act: -0.0000

Data Index: 776477 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1191641 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1523. Min Act: -0.0000

Data Index: 810984 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1495. Min Act: -0.0000

Data Index: 642954 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1281198 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1433. Min Act: -0.0000

Data Index: 570493 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1436. Min Act: -0.0000

Data Index: 259624 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1265069 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1435242 (Python Code)

Max Activating Token Index: 66

Text #19

Max Range: 0.2262. Min Range: -0.2262

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1080537 (C4 (Web Text))

Max Activating Token Index: 1019