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

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

Neuron 2027 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: 0.2124. Min Range: -0.2124

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1622293 (Python Code)

Max Activating Token Index: 845

Text #1

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.2019. Min Act: -0.0000

Data Index: 503908 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1625098 (Python Code)

Max Activating Token Index: 812

Text #3

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1851. Min Act: -0.0000

Data Index: 947499 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1558995 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1566773 (Python Code)

Max Activating Token Index: 751

Text #6

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1447792 (Python Code)

Max Activating Token Index: 826

Text #7

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1824. Min Act: -0.0000

Data Index: 31067 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1424141 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1432. Min Act: -0.0000

Data Index: 578864 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1658. Min Act: -0.0000

Data Index: 215583 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1376324 (Python Code)

Max Activating Token Index: 197

Text #12

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1589. Min Act: 0.0000

Data Index: 88871 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1591566 (Python Code)

Max Activating Token Index: 834

Text #14

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1503947 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1483140 (Python Code)

Max Activating Token Index: 432

Text #16

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1581828 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1530. Min Act: -0.0000

Data Index: 688411 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1539402 (Python Code)

Max Activating Token Index: 577

Text #19

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1601. Min Act: -0.0000

Data Index: 873346 (C4 (Web Text))

Max Activating Token Index: 670