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

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

Neuron 3829 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1540. Min Range: -1.1540

Max Act: 1.1540. Min Act: -0.0001

Data Index: 295426 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 1.1540. Min Range: -1.1540

Max Act: 1.0845. Min Act: -0.0001

Data Index: 132254 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.9758. Min Act: -0.0001

Data Index: 762328 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.9410. Min Act: -0.0001

Data Index: 675748 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.9039. Min Act: -0.0001

Data Index: 206683 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.8631. Min Act: -0.0001

Data Index: 271875 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.8384. Min Act: -0.0001

Data Index: 256882 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.8196. Min Act: -0.0001

Data Index: 985828 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7519. Min Act: -0.0001

Data Index: 954782 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7373. Min Act: -0.0001

Data Index: 935805 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7868. Min Act: -0.0001

Data Index: 1250451 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7167. Min Act: -0.0001

Data Index: 364326 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7656. Min Act: -0.0001

Data Index: 1154741 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7793. Min Act: -0.0001

Data Index: 930233 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7743. Min Act: -0.0001

Data Index: 152976 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.8143. Min Act: -0.0001

Data Index: 693567 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7473. Min Act: -0.0001

Data Index: 179285 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7728. Min Act: -0.0001

Data Index: 354564 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7331. Min Act: -0.0001

Data Index: 144016 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 1.1540. Min Range: -1.1540

Max Act: 0.7585. Min Act: -0.0001

Data Index: 100379 (C4 (Web Text))

Max Activating Token Index: 465