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

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

Neuron 3554 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1525136 (Python Code)

Max Activating Token Index: 362

Text #1

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1459018 (Python Code)

Max Activating Token Index: 729

Text #2

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1627407 (Python Code)

Max Activating Token Index: 563

Text #3

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1399116 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1595601 (Python Code)

Max Activating Token Index: 956

Text #5

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1374209 (Python Code)

Max Activating Token Index: 337

Text #6

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1591999 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1413751 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1404326 (Python Code)

Max Activating Token Index: 153

Text #9

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1479558 (Python Code)

Max Activating Token Index: 549

Text #10

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1391569 (Python Code)

Max Activating Token Index: 823

Text #11

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1418981 (Python Code)

Max Activating Token Index: 858

Text #12

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1461192 (Python Code)

Max Activating Token Index: 784

Text #13

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1538178 (Python Code)

Max Activating Token Index: 707

Text #14

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1571397 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1490498 (Python Code)

Max Activating Token Index: 911

Text #16

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1540328 (Python Code)

Max Activating Token Index: 202

Text #17

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1481250 (Python Code)

Max Activating Token Index: 902

Text #18

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1577347 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 0.7629. Min Range: -0.7629

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1371407 (Python Code)

Max Activating Token Index: 177