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

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

Neuron 2802 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1973. Min Act: -0.0002

Data Index: 1500439 (Python Code)

Max Activating Token Index: 189

Text #1

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1923. Min Act: -0.0002

Data Index: 1363921 (Python Code)

Max Activating Token Index: 241

Text #2

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1809. Min Act: -0.0003

Data Index: 1399123 (Python Code)

Max Activating Token Index: 129

Text #3

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1700. Min Act: -0.0003

Data Index: 1558871 (Python Code)

Max Activating Token Index: 82

Text #4

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1581. Min Act: -0.0002

Data Index: 1570611 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1701. Min Act: -0.0003

Data Index: 1391196 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1685. Min Act: -0.0003

Data Index: 1531135 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1617. Min Act: -0.0003

Data Index: 1490402 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1600. Min Act: -0.0002

Data Index: 1415462 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1663. Min Act: -0.0002

Data Index: 1460871 (Python Code)

Max Activating Token Index: 408

Text #10

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1598. Min Act: -0.0003

Data Index: 1470741 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1629. Min Act: -0.0003

Data Index: 1579293 (Python Code)

Max Activating Token Index: 303

Text #12

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1633. Min Act: -0.0002

Data Index: 1431294 (Python Code)

Max Activating Token Index: 186

Text #13

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1571. Min Act: -0.0003

Data Index: 1446192 (Python Code)

Max Activating Token Index: 335

Text #14

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1570. Min Act: -0.0003

Data Index: 1441158 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1676. Min Act: -0.0002

Data Index: 1504205 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1503. Min Act: -0.0003

Data Index: 1587932 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1610. Min Act: -0.0003

Data Index: 1431519 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1602. Min Act: -0.0002

Data Index: 1446985 (Python Code)

Max Activating Token Index: 506

Text #19

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1578. Min Act: -0.0003

Data Index: 1554668 (Python Code)

Max Activating Token Index: 293