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

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

Neuron 2618 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.9867. Min Act: -0.0001

Data Index: 333034 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8325. Min Act: -0.0002

Data Index: 158397 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8999. Min Act: -0.0001

Data Index: 590083 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8994. Min Act: -0.0002

Data Index: 437748 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.9528. Min Act: -0.0002

Data Index: 667856 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8410. Min Act: -0.0001

Data Index: 1067841 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8970. Min Act: -0.0002

Data Index: 1281316 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8846. Min Act: -0.0002

Data Index: 53567 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.9739. Min Act: -0.0002

Data Index: 118853 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7999. Min Act: -0.0001

Data Index: 122123 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8949. Min Act: -0.0002

Data Index: 663545 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7850. Min Act: -0.0001

Data Index: 391519 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8618. Min Act: -0.0001

Data Index: 582055 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8279. Min Act: -0.0002

Data Index: 552903 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8508. Min Act: -0.0002

Data Index: 962531 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8393. Min Act: -0.0001

Data Index: 1298734 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8808. Min Act: -0.0002

Data Index: 634211 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8141. Min Act: -0.0002

Data Index: 425804 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8645. Min Act: -0.0001

Data Index: 885799 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8629. Min Act: -0.0002

Data Index: 648375 (C4 (Web Text))

Max Activating Token Index: 40