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

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

Neuron 1030 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: 2.4894. Min Range: -2.4894

Max Act: 2.3546. Min Act: -0.0000

Data Index: 1534686 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.4618. Min Act: -0.0000

Data Index: 1503298 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.4894. Min Act: -0.0000

Data Index: 1604417 (Python Code)

Max Activating Token Index: 271

Text #3

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.3564. Min Act: -0.0000

Data Index: 1627049 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.2237. Min Act: -0.0000

Data Index: 1535911 (Python Code)

Max Activating Token Index: 896

Text #5

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.2767. Min Act: -0.0000

Data Index: 1565321 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.3062. Min Act: -0.0000

Data Index: 1648800 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.0712. Min Act: -0.0000

Data Index: 1569163 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.1711. Min Act: -0.0000

Data Index: 1394393 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.1517. Min Act: -0.0000

Data Index: 1379344 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.2536. Min Act: -0.0000

Data Index: 1628868 (Python Code)

Max Activating Token Index: 478

Text #11

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.3381. Min Act: -0.0000

Data Index: 1431094 (Python Code)

Max Activating Token Index: 226

Text #12

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.0667. Min Act: -0.0000

Data Index: 1647853 (Python Code)

Max Activating Token Index: 867

Text #13

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.3035. Min Act: -0.0000

Data Index: 1403232 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.0852. Min Act: -0.0000

Data Index: 1496073 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.2167. Min Act: -0.0000

Data Index: 1573368 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.0793. Min Act: -0.0000

Data Index: 1390369 (Python Code)

Max Activating Token Index: 702

Text #17

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.1222. Min Act: -0.0000

Data Index: 1594329 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.0194. Min Act: -0.0000

Data Index: 1643064 (Python Code)

Max Activating Token Index: 970

Text #19

Max Range: 2.4894. Min Range: -2.4894

Max Act: 2.2096. Min Act: -0.0000

Data Index: 1438213 (Python Code)

Max Activating Token Index: 321