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

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

Neuron 3886 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0889. Min Range: -3.0889

Max Act: 3.0889. Min Act: -0.0000

Data Index: 1405168 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 3.0889. Min Range: -3.0889

Max Act: 3.0777. Min Act: -0.0000

Data Index: 1640289 (Python Code)

Max Activating Token Index: 95

Text #2

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.6556. Min Act: -0.0000

Data Index: 1631484 (Python Code)

Max Activating Token Index: 936

Text #3

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.7687. Min Act: -0.0000

Data Index: 1589080 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.7557. Min Act: -0.0000

Data Index: 1412602 (Python Code)

Max Activating Token Index: 574

Text #5

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.7039. Min Act: -0.0000

Data Index: 1504410 (Python Code)

Max Activating Token Index: 596

Text #6

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.5651. Min Act: -0.0000

Data Index: 1568528 (Python Code)

Max Activating Token Index: 171

Text #7

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.5528. Min Act: -0.0000

Data Index: 1574019 (Python Code)

Max Activating Token Index: 786

Text #8

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.8095. Min Act: -0.0000

Data Index: 1495138 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.6518. Min Act: -0.0000

Data Index: 1385835 (Python Code)

Max Activating Token Index: 625

Text #10

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.6177. Min Act: -0.0000

Data Index: 1477399 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.4814. Min Act: -0.0000

Data Index: 1455841 (Python Code)

Max Activating Token Index: 277

Text #12

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.5934. Min Act: -0.0000

Data Index: 1433280 (Python Code)

Max Activating Token Index: 352

Text #13

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.7306. Min Act: -0.0000

Data Index: 1622721 (Python Code)

Max Activating Token Index: 574

Text #14

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.5751. Min Act: -0.0000

Data Index: 1497914 (Python Code)

Max Activating Token Index: 722

Text #15

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.5545. Min Act: -0.0000

Data Index: 1464961 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.3092. Min Act: -0.0000

Data Index: 1611811 (Python Code)

Max Activating Token Index: 837

Text #17

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.4159. Min Act: -0.0000

Data Index: 1638886 (Python Code)

Max Activating Token Index: 354

Text #18

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.2990. Min Act: -0.0000

Data Index: 1558442 (Python Code)

Max Activating Token Index: 879

Text #19

Max Range: 3.0889. Min Range: -3.0889

Max Act: 2.3930. Min Act: -0.0000

Data Index: 1410024 (Python Code)

Max Activating Token Index: 715