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

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

Neuron 2610 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: 0.2290. Min Range: -0.2290

Max Act: 0.2290. Min Act: -0.0000

Data Index: 223792 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1109553 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1009432 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1753. Min Act: -0.0000

Data Index: 349121 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1647. Min Act: -0.0000

Data Index: 548692 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1342829 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1596. Min Act: -0.0000

Data Index: 704505 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1536. Min Act: -0.0000

Data Index: 980870 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1479433 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1524. Min Act: -0.0000

Data Index: 248855 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1496. Min Act: -0.0000

Data Index: 683580 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1001050 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1472. Min Act: -0.0000

Data Index: 533411 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1505. Min Act: -0.0000

Data Index: 748486 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1451. Min Act: -0.0000

Data Index: 518891 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1487. Min Act: -0.0000

Data Index: 105421 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1438. Min Act: -0.0000

Data Index: 643915 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1511528 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1412. Min Act: -0.0000

Data Index: 174387 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1411. Min Act: -0.0000

Data Index: 981700 (C4 (Web Text))

Max Activating Token Index: 68