Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1112 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1393426 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0005

Data Index: 86128 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0096. Min Act: -0.0005

Data Index: 1373308 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0095. Min Act: -0.0005

Data Index: 971188 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1632341 (Python Code)

Max Activating Token Index: 857

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1410908 (Python Code)

Max Activating Token Index: 667

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0094. Min Act: -0.0005

Data Index: 859238 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1512725 (Python Code)

Max Activating Token Index: 969

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0093. Min Act: -0.0005

Data Index: 13597 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0093. Min Act: -0.0005

Data Index: 1496379 (Python Code)

Max Activating Token Index: 881

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1529567 (Python Code)

Max Activating Token Index: 482

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0095. Min Act: -0.0005

Data Index: 122035 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0091. Min Act: -0.0005

Data Index: 1646736 (Python Code)

Max Activating Token Index: 898

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1532095 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1547848 (Python Code)

Max Activating Token Index: 65

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1554828 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1439574 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1451720 (Python Code)

Max Activating Token Index: 905

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0091. Min Act: -0.0005

Data Index: 1395647 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0091. Min Act: -0.0005

Data Index: 1588901 (Python Code)

Max Activating Token Index: 23