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

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

Neuron 403 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0737. Min Act: -0.0003

Data Index: 1643332 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0674. Min Act: -0.0003

Data Index: 1651004 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0401. Min Act: -0.0003

Data Index: 1634280 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0070. Min Act: -0.0002

Data Index: 1485372 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9897. Min Act: -0.0003

Data Index: 1497312 (Python Code)

Max Activating Token Index: 342

Text #5

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0112. Min Act: -0.0002

Data Index: 1564154 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0031. Min Act: -0.0003

Data Index: 1544245 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9475. Min Act: -0.0003

Data Index: 1362089 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0258. Min Act: -0.0003

Data Index: 1419137 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9859. Min Act: -0.0003

Data Index: 1396696 (Python Code)

Max Activating Token Index: 533

Text #10

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9841. Min Act: -0.0002

Data Index: 1510946 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9703. Min Act: -0.0003

Data Index: 1541856 (Python Code)

Max Activating Token Index: 86

Text #12

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9656. Min Act: -0.0003

Data Index: 1443327 (Python Code)

Max Activating Token Index: 376

Text #13

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9615. Min Act: -0.0003

Data Index: 1620855 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9618. Min Act: -0.0003

Data Index: 1428495 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9664. Min Act: -0.0003

Data Index: 1508207 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9837. Min Act: -0.0003

Data Index: 1499488 (Python Code)

Max Activating Token Index: 956

Text #17

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9624. Min Act: -0.0003

Data Index: 1517735 (Python Code)

Max Activating Token Index: 615

Text #18

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9553. Min Act: -0.0002

Data Index: 1598381 (Python Code)

Max Activating Token Index: 332

Text #19

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9491. Min Act: -0.0003

Data Index: 1398855 (Python Code)

Max Activating Token Index: 566