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

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

Neuron 4258 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1314535 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1570230 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1373730 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1426235 (Python Code)

Max Activating Token Index: 678

Text #4

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1140401 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1842. Min Act: -0.0000

Data Index: 30565 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1700. Min Act: -0.0000

Data Index: 919683 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1734. Min Act: -0.0000

Data Index: 343379 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1518406 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1662. Min Act: -0.0000

Data Index: 174263 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1398533 (Python Code)

Max Activating Token Index: 661

Text #11

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1662. Min Act: -0.0000

Data Index: 814239 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1366642 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1550. Min Act: -0.0000

Data Index: 898612 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1593334 (Python Code)

Max Activating Token Index: 127

Text #15

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1630. Min Act: -0.0000

Data Index: 375104 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1456. Min Act: -0.0000

Data Index: 230398 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1544872 (Python Code)

Max Activating Token Index: 103

Text #18

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1559. Min Act: -0.0000

Data Index: 546622 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1094340 (C4 (Web Text))

Max Activating Token Index: 1012