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

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

Neuron 5977 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3603. Min Range: -3.3603

Max Act: 3.3603. Min Act: -0.0000

Data Index: 325132 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 3.3603. Min Range: -3.3603

Max Act: 3.1298. Min Act: -0.0000

Data Index: 464104 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.9912. Min Act: -0.0000

Data Index: 713041 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 3.3603. Min Range: -3.3603

Max Act: 3.1020. Min Act: -0.0000

Data Index: 579748 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.8220. Min Act: -0.0000

Data Index: 712596 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.9030. Min Act: -0.0000

Data Index: 1116951 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.7720. Min Act: -0.0000

Data Index: 20859 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.8200. Min Act: -0.0000

Data Index: 350324 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.4700. Min Act: -0.0000

Data Index: 1017783 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.2891. Min Act: -0.0000

Data Index: 330299 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.1239. Min Act: -0.0000

Data Index: 848239 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.1379. Min Act: -0.0000

Data Index: 578556 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.2907. Min Act: -0.0000

Data Index: 241827 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.1118. Min Act: -0.0000

Data Index: 38317 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.1200. Min Act: -0.0000

Data Index: 916256 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.2388. Min Act: -0.0000

Data Index: 453451 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 3.3603. Min Range: -3.3603

Max Act: 1.9624. Min Act: -0.0000

Data Index: 47189 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.0581. Min Act: -0.0000

Data Index: 1171274 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.0120. Min Act: -0.0000

Data Index: 98253 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 3.3603. Min Range: -3.3603

Max Act: 2.1134. Min Act: -0.0000

Data Index: 54218 (C4 (Web Text))

Max Activating Token Index: 593