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

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

Neuron 439 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1130. Min Act: -0.0001

Data Index: 187419 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1059. Min Act: -0.0001

Data Index: 303627 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1304335 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0974. Min Act: -0.0001

Data Index: 577903 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0807. Min Act: -0.0001

Data Index: 45056 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0774. Min Act: -0.0001

Data Index: 924860 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0811. Min Act: -0.0001

Data Index: 884197 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1078001 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0739. Min Act: -0.0001

Data Index: 370712 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0785. Min Act: -0.0001

Data Index: 732073 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0733. Min Act: -0.0001

Data Index: 61211 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0778. Min Act: -0.0001

Data Index: 587228 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0721. Min Act: -0.0001

Data Index: 701725 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0747. Min Act: -0.0001

Data Index: 913011 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0693. Min Act: -0.0001

Data Index: 13272 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0707. Min Act: -0.0001

Data Index: 863344 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0675. Min Act: -0.0001

Data Index: 354388 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0723. Min Act: -0.0001

Data Index: 85144 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0697. Min Act: -0.0001

Data Index: 608514 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1243473 (C4 (Web Text))

Max Activating Token Index: 876