Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2229 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.9684. Min Act: -0.0000

Data Index: 1447595 (Python Code)

Max Activating Token Index: 461

Text #1

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.9696. Min Act: 0.0000

Data Index: 1385140 (Python Code)

Max Activating Token Index: 629

Text #2

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.9359. Min Act: 0.0000

Data Index: 1437568 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.6048. Min Act: 0.0000

Data Index: 1581980 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.2586. Min Act: 0.0000

Data Index: 1460574 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.0031. Min Act: -0.0000

Data Index: 1528155 (Python Code)

Max Activating Token Index: 168

Text #6

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.9796. Min Act: 0.0000

Data Index: 1516287 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.0635. Min Act: -0.0000

Data Index: 1476118 (Python Code)

Max Activating Token Index: 157

Text #8

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.1925. Min Act: -0.0000

Data Index: 14738 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.0354. Min Act: -0.0000

Data Index: 1375026 (Python Code)

Max Activating Token Index: 460

Text #10

Max Range: 3.9696. Min Range: -3.9696

Max Act: 3.1424. Min Act: -0.0000

Data Index: 1391859 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.9615. Min Act: -0.0000

Data Index: 1563163 (Python Code)

Max Activating Token Index: 737

Text #12

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.9097. Min Act: -0.0000

Data Index: 1442827 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.9151. Min Act: -0.0000

Data Index: 1412332 (Python Code)

Max Activating Token Index: 770

Text #14

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.8777. Min Act: 0.0000

Data Index: 1568201 (Python Code)

Max Activating Token Index: 458

Text #15

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.7445. Min Act: -0.0000

Data Index: 1609071 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.8766. Min Act: 0.0000

Data Index: 1379802 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.8319. Min Act: -0.0000

Data Index: 1608976 (Python Code)

Max Activating Token Index: 878

Text #18

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.8680. Min Act: -0.0000

Data Index: 1557045 (Python Code)

Max Activating Token Index: 271

Text #19

Max Range: 3.9696. Min Range: -3.9696

Max Act: 2.6731. Min Act: -0.0000

Data Index: 1623584 (Python Code)

Max Activating Token Index: 222