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

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

Neuron 3659 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3503. Min Range: -2.3503

Max Act: 2.3503. Min Act: -0.0000

Data Index: 1577520 (Python Code)

Max Activating Token Index: 636

Text #1

Max Range: 2.3503. Min Range: -2.3503

Max Act: 2.0210. Min Act: -0.0000

Data Index: 1451785 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 2.3503. Min Range: -2.3503

Max Act: 2.0765. Min Act: -0.0000

Data Index: 1616290 (Python Code)

Max Activating Token Index: 347

Text #3

Max Range: 2.3503. Min Range: -2.3503

Max Act: 2.1071. Min Act: -0.0000

Data Index: 1472299 (Python Code)

Max Activating Token Index: 831

Text #4

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.8685. Min Act: -0.0000

Data Index: 1539931 (Python Code)

Max Activating Token Index: 349

Text #5

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.9648. Min Act: -0.0000

Data Index: 1368219 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.8452. Min Act: -0.0000

Data Index: 1443700 (Python Code)

Max Activating Token Index: 628

Text #7

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.8894. Min Act: -0.0000

Data Index: 1516359 (Python Code)

Max Activating Token Index: 530

Text #8

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.9276. Min Act: -0.0000

Data Index: 1445745 (Python Code)

Max Activating Token Index: 759

Text #9

Max Range: 2.3503. Min Range: -2.3503

Max Act: 2.0482. Min Act: -0.0000

Data Index: 1362563 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.9668. Min Act: -0.0000

Data Index: 1528183 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 2.3503. Min Range: -2.3503

Max Act: 2.0287. Min Act: -0.0000

Data Index: 1389300 (Python Code)

Max Activating Token Index: 467

Text #12

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.7960. Min Act: -0.0000

Data Index: 1434980 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.9579. Min Act: -0.0000

Data Index: 1496466 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.9579. Min Act: -0.0000

Data Index: 1502949 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.9548. Min Act: -0.0000

Data Index: 1555340 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.8916. Min Act: -0.0000

Data Index: 1479142 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.8916. Min Act: -0.0000

Data Index: 1365462 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.8357. Min Act: -0.0000

Data Index: 1361479 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 2.3503. Min Range: -2.3503

Max Act: 1.7248. Min Act: -0.0000

Data Index: 1489851 (Python Code)

Max Activating Token Index: 26