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

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

Neuron 2396 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.9459. Min Act: -0.0000

Data Index: 1649878 (Python Code)

Max Activating Token Index: 445

Text #1

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.9853. Min Act: -0.0000

Data Index: 1605112 (Python Code)

Max Activating Token Index: 838

Text #2

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.5863. Min Act: -0.0000

Data Index: 1438980 (Python Code)

Max Activating Token Index: 629

Text #3

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.7023. Min Act: -0.0000

Data Index: 1384156 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.6868. Min Act: -0.0000

Data Index: 1602339 (Python Code)

Max Activating Token Index: 518

Text #5

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.6168. Min Act: -0.0000

Data Index: 1528340 (Python Code)

Max Activating Token Index: 623

Text #6

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.5500. Min Act: -0.0000

Data Index: 1597291 (Python Code)

Max Activating Token Index: 757

Text #7

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.3823. Min Act: -0.0000

Data Index: 1517153 (Python Code)

Max Activating Token Index: 556

Text #8

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.3846. Min Act: -0.0000

Data Index: 1505757 (Python Code)

Max Activating Token Index: 258

Text #9

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.3611. Min Act: -0.0000

Data Index: 1455902 (Python Code)

Max Activating Token Index: 384

Text #10

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.4692. Min Act: -0.0000

Data Index: 1457627 (Python Code)

Max Activating Token Index: 715

Text #11

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.4202. Min Act: -0.0000

Data Index: 1553841 (Python Code)

Max Activating Token Index: 536

Text #12

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.2924. Min Act: -0.0000

Data Index: 1431773 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.1644. Min Act: -0.0000

Data Index: 1620724 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.2709. Min Act: -0.0000

Data Index: 1477811 (Python Code)

Max Activating Token Index: 926

Text #15

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.3430. Min Act: -0.0000

Data Index: 1581764 (Python Code)

Max Activating Token Index: 302

Text #16

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.2140. Min Act: -0.0000

Data Index: 1369758 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.2096. Min Act: -0.0000

Data Index: 1587082 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.0841. Min Act: -0.0000

Data Index: 1546368 (Python Code)

Max Activating Token Index: 865

Text #19

Max Range: 2.9853. Min Range: -2.9853

Max Act: 2.2782. Min Act: -0.0000

Data Index: 1542032 (Python Code)

Max Activating Token Index: 535