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

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

Neuron 4959 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.2072. Min Act: -0.0002

Data Index: 1614986 (Python Code)

Max Activating Token Index: 121

Text #1

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1813. Min Act: -0.0002

Data Index: 1371908 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1872. Min Act: -0.0002

Data Index: 1565622 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1724. Min Act: -0.0002

Data Index: 1486500 (Python Code)

Max Activating Token Index: 180

Text #4

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1715. Min Act: -0.0002

Data Index: 1553727 (Python Code)

Max Activating Token Index: 187

Text #5

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1582. Min Act: -0.0002

Data Index: 1413171 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1447. Min Act: -0.0002

Data Index: 1386858 (Python Code)

Max Activating Token Index: 275

Text #7

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1549. Min Act: -0.0002

Data Index: 1599789 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1455. Min Act: -0.0002

Data Index: 1450936 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1556. Min Act: -0.0002

Data Index: 1598066 (Python Code)

Max Activating Token Index: 418

Text #10

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1532. Min Act: -0.0002

Data Index: 1414951 (Python Code)

Max Activating Token Index: 419

Text #11

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1476. Min Act: -0.0002

Data Index: 1586805 (Python Code)

Max Activating Token Index: 460

Text #12

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1473. Min Act: -0.0002

Data Index: 1588783 (Python Code)

Max Activating Token Index: 826

Text #13

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1562. Min Act: -0.0002

Data Index: 1447361 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1510. Min Act: -0.0002

Data Index: 1623668 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1639. Min Act: -0.0002

Data Index: 1601496 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1428. Min Act: -0.0002

Data Index: 1555001 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1309. Min Act: -0.0002

Data Index: 1420649 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1450. Min Act: -0.0002

Data Index: 1596439 (Python Code)

Max Activating Token Index: 285

Text #19

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1532. Min Act: -0.0002

Data Index: 1602360 (Python Code)

Max Activating Token Index: 715