Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 697 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.8717. Min Act: -0.0000

Data Index: 1051028 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.8651. Min Act: -0.0000

Data Index: 218808 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.6599. Min Act: -0.0001

Data Index: 1198021 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.5948. Min Act: -0.0001

Data Index: 269228 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.5870. Min Act: -0.0001

Data Index: 975408 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.5377. Min Act: -0.0000

Data Index: 282756 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4751. Min Act: -0.0001

Data Index: 1133039 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.5031. Min Act: -0.0001

Data Index: 318725 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4786. Min Act: -0.0001

Data Index: 157309 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.5228. Min Act: -0.0001

Data Index: 1357556 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.5234. Min Act: -0.0001

Data Index: 1081583 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4709. Min Act: -0.0001

Data Index: 354319 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4660. Min Act: -0.0001

Data Index: 26292 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.5530. Min Act: -0.0001

Data Index: 854967 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4099. Min Act: -0.0001

Data Index: 81759 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4505. Min Act: -0.0000

Data Index: 337231 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4497. Min Act: -0.0001

Data Index: 758714 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4005. Min Act: -0.0001

Data Index: 192689 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4373. Min Act: -0.0001

Data Index: 353458 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 1.8717. Min Range: -1.8717

Max Act: 1.4326. Min Act: -0.0001

Data Index: 1121865 (C4 (Web Text))

Max Activating Token Index: 577