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

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

Neuron 5209 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.5391. Min Act: -0.0002

Data Index: 1590457 (Python Code)

Max Activating Token Index: 188

Text #1

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4980. Min Act: -0.0002

Data Index: 1476329 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4614. Min Act: -0.0002

Data Index: 1562665 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4644. Min Act: -0.0002

Data Index: 1611074 (Python Code)

Max Activating Token Index: 796

Text #4

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4205. Min Act: -0.0002

Data Index: 1499163 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4051. Min Act: -0.0002

Data Index: 1576124 (Python Code)

Max Activating Token Index: 934

Text #6

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3929. Min Act: -0.0002

Data Index: 1450781 (Python Code)

Max Activating Token Index: 1010

Text #7

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3774. Min Act: -0.0002

Data Index: 1440146 (Python Code)

Max Activating Token Index: 683

Text #8

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4124. Min Act: -0.0002

Data Index: 1586829 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3864. Min Act: -0.0002

Data Index: 1447411 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4089. Min Act: -0.0002

Data Index: 1405422 (Python Code)

Max Activating Token Index: 918

Text #11

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3977. Min Act: -0.0002

Data Index: 1585384 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3610. Min Act: -0.0002

Data Index: 1603984 (Python Code)

Max Activating Token Index: 911

Text #13

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3574. Min Act: -0.0002

Data Index: 1547952 (Python Code)

Max Activating Token Index: 188

Text #14

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3379. Min Act: -0.0002

Data Index: 1418196 (Python Code)

Max Activating Token Index: 454

Text #15

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3629. Min Act: -0.0002

Data Index: 1433291 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3379. Min Act: -0.0002

Data Index: 1431638 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3459. Min Act: -0.0002

Data Index: 1587333 (Python Code)

Max Activating Token Index: 474

Text #18

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3289. Min Act: -0.0002

Data Index: 1462515 (Python Code)

Max Activating Token Index: 902

Text #19

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3535. Min Act: -0.0002

Data Index: 1632553 (Python Code)

Max Activating Token Index: 189