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

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

Neuron 3980 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1594143 (Python Code)

Max Activating Token Index: 473

Text #1

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1469774 (Python Code)

Max Activating Token Index: 527

Text #2

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1420021 (Python Code)

Max Activating Token Index: 455

Text #3

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1408380 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1455741 (Python Code)

Max Activating Token Index: 549

Text #5

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1417105 (Python Code)

Max Activating Token Index: 149

Text #6

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1449286 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1633077 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1519606 (Python Code)

Max Activating Token Index: 549

Text #9

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1407280 (Python Code)

Max Activating Token Index: 698

Text #10

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1527887 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1416778 (Python Code)

Max Activating Token Index: 882

Text #12

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4191. Min Act: -0.0001

Data Index: 1638252 (Python Code)

Max Activating Token Index: 629

Text #13

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1530225 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1492635 (Python Code)

Max Activating Token Index: 313

Text #15

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1449994 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1547166 (Python Code)

Max Activating Token Index: 676

Text #17

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1594727 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1397522 (Python Code)

Max Activating Token Index: 879

Text #19

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1419584 (Python Code)

Max Activating Token Index: 82