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

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

Neuron 5735 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.6778. Min Act: -0.0000

Data Index: 1439985 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.7433. Min Act: -0.0000

Data Index: 1517799 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.4608. Min Act: -0.0000

Data Index: 1418770 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 5.7433. Min Range: -5.7433

Max Act: 4.5296. Min Act: -0.0000

Data Index: 1553272 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 5.7433. Min Range: -5.7433

Max Act: 4.7284. Min Act: -0.0000

Data Index: 1432569 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 5.7433. Min Range: -5.7433

Max Act: 4.4034. Min Act: -0.0000

Data Index: 1530951 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 5.7433. Min Range: -5.7433

Max Act: 4.2338. Min Act: -0.0000

Data Index: 1388071 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.9457. Min Act: -0.0000

Data Index: 1449288 (Python Code)

Max Activating Token Index: 994

Text #8

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.8019. Min Act: -0.0000

Data Index: 1527783 (Python Code)

Max Activating Token Index: 201

Text #9

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.5667. Min Act: -0.0000

Data Index: 1416890 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.4977. Min Act: -0.0000

Data Index: 1546837 (Python Code)

Max Activating Token Index: 881

Text #11

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.2111. Min Act: -0.0000

Data Index: 1515862 (Python Code)

Max Activating Token Index: 427

Text #12

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.1833. Min Act: -0.0000

Data Index: 1619773 (Python Code)

Max Activating Token Index: 803

Text #13

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.4484. Min Act: -0.0000

Data Index: 1542124 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.3107. Min Act: -0.0000

Data Index: 1438664 (Python Code)

Max Activating Token Index: 646

Text #15

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.3487. Min Act: -0.0000

Data Index: 1560199 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.1969. Min Act: -0.0000

Data Index: 1590293 (Python Code)

Max Activating Token Index: 637

Text #17

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.3264. Min Act: -0.0000

Data Index: 1410653 (Python Code)

Max Activating Token Index: 952

Text #18

Max Range: 5.7433. Min Range: -5.7433

Max Act: 3.1607. Min Act: -0.0000

Data Index: 1447339 (Python Code)

Max Activating Token Index: 804

Text #19

Max Range: 5.7433. Min Range: -5.7433

Max Act: 2.6422. Min Act: -0.0000

Data Index: 1544178 (Python Code)

Max Activating Token Index: 955