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

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

Neuron 1799 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: 3.5335. Min Range: -3.5335

Max Act: 3.5122. Min Act: -0.0000

Data Index: 1450166 (Python Code)

Max Activating Token Index: 1012

Text #1

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.5335. Min Act: -0.0000

Data Index: 1426573 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.5112. Min Act: -0.0000

Data Index: 1612430 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.3040. Min Act: -0.0000

Data Index: 1634213 (Python Code)

Max Activating Token Index: 503

Text #4

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.1524. Min Act: -0.0000

Data Index: 1454847 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.2985. Min Act: -0.0000

Data Index: 1528466 (Python Code)

Max Activating Token Index: 803

Text #6

Max Range: 3.5335. Min Range: -3.5335

Max Act: 3.0509. Min Act: -0.0000

Data Index: 1643822 (Python Code)

Max Activating Token Index: 376

Text #7

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.9536. Min Act: -0.0000

Data Index: 1592142 (Python Code)

Max Activating Token Index: 837

Text #8

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.7727. Min Act: -0.0000

Data Index: 1595159 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.8541. Min Act: -0.0000

Data Index: 1548226 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.8064. Min Act: -0.0000

Data Index: 1471333 (Python Code)

Max Activating Token Index: 325

Text #11

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.7717. Min Act: -0.0000

Data Index: 1466059 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.4958. Min Act: -0.0000

Data Index: 1499304 (Python Code)

Max Activating Token Index: 863

Text #13

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.6371. Min Act: -0.0000

Data Index: 1440597 (Python Code)

Max Activating Token Index: 25

Text #14

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.7475. Min Act: -0.0000

Data Index: 1485154 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.8749. Min Act: -0.0000

Data Index: 1369564 (Python Code)

Max Activating Token Index: 776

Text #16

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.7111. Min Act: -0.0000

Data Index: 1577375 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.5593. Min Act: -0.0000

Data Index: 1508160 (Python Code)

Max Activating Token Index: 370

Text #18

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.5524. Min Act: -0.0000

Data Index: 1648618 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 3.5335. Min Range: -3.5335

Max Act: 2.7667. Min Act: -0.0000

Data Index: 1442963 (Python Code)

Max Activating Token Index: 813