Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1678 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1652. Min Act: -0.0003

Data Index: 1445141 (Python Code)

Max Activating Token Index: 383

Text #1

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1641. Min Act: -0.0003

Data Index: 1618767 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1663. Min Act: -0.0002

Data Index: 1631680 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1672. Min Act: -0.0003

Data Index: 1562613 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1615. Min Act: -0.0003

Data Index: 1428117 (Python Code)

Max Activating Token Index: 470

Text #5

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1657. Min Act: -0.0003

Data Index: 1588598 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1657. Min Act: -0.0003

Data Index: 1536154 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1657. Min Act: -0.0003

Data Index: 1360322 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1556. Min Act: -0.0003

Data Index: 1640358 (Python Code)

Max Activating Token Index: 85

Text #9

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1613. Min Act: -0.0003

Data Index: 1572549 (Python Code)

Max Activating Token Index: 715

Text #10

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1571. Min Act: -0.0004

Data Index: 1468692 (Python Code)

Max Activating Token Index: 793

Text #11

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1543. Min Act: -0.0003

Data Index: 1362337 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1535. Min Act: -0.0003

Data Index: 1510358 (Python Code)

Max Activating Token Index: 734

Text #13

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1585. Min Act: -0.0003

Data Index: 1581509 (Python Code)

Max Activating Token Index: 421

Text #14

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1600. Min Act: -0.0003

Data Index: 1444391 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1556. Min Act: -0.0003

Data Index: 1531454 (Python Code)

Max Activating Token Index: 564

Text #16

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1487. Min Act: -0.0003

Data Index: 1654195 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1517. Min Act: -0.0003

Data Index: 1566855 (Python Code)

Max Activating Token Index: 313

Text #18

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1564. Min Act: -0.0003

Data Index: 1593021 (Python Code)

Max Activating Token Index: 318

Text #19

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1498. Min Act: -0.0003

Data Index: 1596786 (Python Code)

Max Activating Token Index: 988