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

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

Neuron 2502 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1496891 (Python Code)

Max Activating Token Index: 741

Text #1

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1451988 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1993. Min Act: -0.0000

Data Index: 585732 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1507014 (Python Code)

Max Activating Token Index: 619

Text #4

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1611083 (Python Code)

Max Activating Token Index: 452

Text #5

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1292278 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1490960 (Python Code)

Max Activating Token Index: 916

Text #7

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1647140 (Python Code)

Max Activating Token Index: 102

Text #8

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1601. Min Act: -0.0000

Data Index: 73225 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1660. Min Act: -0.0000

Data Index: 249575 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1459898 (Python Code)

Max Activating Token Index: 702

Text #11

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1631. Min Act: -0.0000

Data Index: 907759 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1568130 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1561. Min Act: -0.0000

Data Index: 664644 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1486. Min Act: -0.0000

Data Index: 831796 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1512406 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1457. Min Act: -0.0000

Data Index: 890327 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1078962 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1565. Min Act: -0.0000

Data Index: 525410 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1204996 (C4 (Web Text))

Max Activating Token Index: 980