Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1531 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.1420. Min Act: -0.0001

Data Index: 1537825 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0689. Min Act: -0.0001

Data Index: 1425634 (Python Code)

Max Activating Token Index: 986

Text #2

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0608. Min Act: -0.0001

Data Index: 1434517 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0510. Min Act: -0.0001

Data Index: 1533235 (Python Code)

Max Activating Token Index: 333

Text #4

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9856. Min Act: -0.0001

Data Index: 1526987 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0766. Min Act: -0.0001

Data Index: 1481485 (Python Code)

Max Activating Token Index: 566

Text #6

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.1102. Min Act: -0.0001

Data Index: 1413153 (Python Code)

Max Activating Token Index: 549

Text #7

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0331. Min Act: -0.0001

Data Index: 1555099 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0669. Min Act: -0.0001

Data Index: 1487140 (Python Code)

Max Activating Token Index: 827

Text #9

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0074. Min Act: -0.0001

Data Index: 1592025 (Python Code)

Max Activating Token Index: 698

Text #10

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9694. Min Act: -0.0001

Data Index: 1442787 (Python Code)

Max Activating Token Index: 370

Text #11

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9611. Min Act: -0.0001

Data Index: 1435843 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9629. Min Act: -0.0001

Data Index: 1405881 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 1.1420. Min Range: -1.1420

Max Act: 1.0066. Min Act: -0.0001

Data Index: 1608194 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9554. Min Act: -0.0001

Data Index: 1635250 (Python Code)

Max Activating Token Index: 672

Text #15

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9765. Min Act: -0.0001

Data Index: 1541004 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9457. Min Act: -0.0001

Data Index: 1421101 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.8958. Min Act: -0.0001

Data Index: 1562055 (Python Code)

Max Activating Token Index: 506

Text #18

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9811. Min Act: -0.0001

Data Index: 1635451 (Python Code)

Max Activating Token Index: 236

Text #19

Max Range: 1.1420. Min Range: -1.1420

Max Act: 0.9573. Min Act: -0.0001

Data Index: 1452161 (Python Code)

Max Activating Token Index: 479