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

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

Neuron 424 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: 3.4820. Min Range: -3.4820

Max Act: 3.4820. Min Act: -0.0001

Data Index: 1643650 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.4259. Min Act: -0.0001

Data Index: 1606813 (Python Code)

Max Activating Token Index: 530

Text #2

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.4514. Min Act: -0.0001

Data Index: 1471471 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.4398. Min Act: -0.0001

Data Index: 1478426 (Python Code)

Max Activating Token Index: 352

Text #4

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.1131. Min Act: -0.0001

Data Index: 1376974 (Python Code)

Max Activating Token Index: 914

Text #5

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2212. Min Act: -0.0001

Data Index: 1503479 (Python Code)

Max Activating Token Index: 249

Text #6

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.3846. Min Act: -0.0001

Data Index: 1398498 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.0811. Min Act: -0.0001

Data Index: 1631015 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.3444. Min Act: -0.0001

Data Index: 1391434 (Python Code)

Max Activating Token Index: 648

Text #9

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2136. Min Act: -0.0001

Data Index: 1438119 (Python Code)

Max Activating Token Index: 900

Text #10

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.4519. Min Act: -0.0001

Data Index: 1587495 (Python Code)

Max Activating Token Index: 699

Text #11

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.0029. Min Act: -0.0001

Data Index: 1459747 (Python Code)

Max Activating Token Index: 93

Text #12

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.1736. Min Act: -0.0001

Data Index: 1514948 (Python Code)

Max Activating Token Index: 778

Text #13

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2783. Min Act: -0.0001

Data Index: 1648742 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.1148. Min Act: -0.0001

Data Index: 1544516 (Python Code)

Max Activating Token Index: 569

Text #15

Max Range: 3.4820. Min Range: -3.4820

Max Act: 2.9436. Min Act: -0.0001

Data Index: 1420824 (Python Code)

Max Activating Token Index: 679

Text #16

Max Range: 3.4820. Min Range: -3.4820

Max Act: 2.9782. Min Act: -0.0001

Data Index: 1432123 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 3.4820. Min Range: -3.4820

Max Act: 2.9624. Min Act: -0.0001

Data Index: 1422955 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.0603. Min Act: -0.0001

Data Index: 1558442 (Python Code)

Max Activating Token Index: 1002

Text #19

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.0699. Min Act: -0.0001

Data Index: 1618580 (Python Code)

Max Activating Token Index: 378