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

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

Neuron 2768 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3900. Min Range: -2.3900

Max Act: 2.3900. Min Act: -0.0000

Data Index: 156550 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 2.3900. Min Range: -2.3900

Max Act: 2.1544. Min Act: -0.0000

Data Index: 1328553 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 2.3900. Min Range: -2.3900

Max Act: 2.1941. Min Act: -0.0000

Data Index: 889403 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 2.3900. Min Range: -2.3900

Max Act: 2.0701. Min Act: -0.0000

Data Index: 926827 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.9089. Min Act: -0.0000

Data Index: 607354 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.9314. Min Act: -0.0000

Data Index: 1339342 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.9251. Min Act: -0.0000

Data Index: 728738 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.7951. Min Act: -0.0000

Data Index: 444303 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.7643. Min Act: -0.0000

Data Index: 658098 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.7772. Min Act: -0.0000

Data Index: 1315915 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1340666 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.6538. Min Act: -0.0000

Data Index: 571580 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.8227. Min Act: -0.0000

Data Index: 315610 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.6341. Min Act: -0.0000

Data Index: 567560 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.7256. Min Act: -0.0000

Data Index: 1337484 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.7171. Min Act: -0.0000

Data Index: 513507 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.7164. Min Act: -0.0000

Data Index: 752463 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.7843. Min Act: -0.0000

Data Index: 61178 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.7649. Min Act: -0.0000

Data Index: 1344938 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 2.3900. Min Range: -2.3900

Max Act: 1.6769. Min Act: -0.0000

Data Index: 1047030 (C4 (Web Text))

Max Activating Token Index: 139