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

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

Neuron 3775 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1998. Min Act: -0.0000

Data Index: 104798 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1965. Min Act: -0.0000

Data Index: 815149 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1170554 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1870. Min Act: -0.0000

Data Index: 539287 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1859. Min Act: -0.0000

Data Index: 237708 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1013227 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1749. Min Act: -0.0000

Data Index: 1012976 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1788. Min Act: -0.0000

Data Index: 89038 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1723. Min Act: 0.0000

Data Index: 697869 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1712. Min Act: 0.0000

Data Index: 460943 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1646. Min Act: -0.0001

Data Index: 644168 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1647. Min Act: 0.0000

Data Index: 786030 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1675. Min Act: 0.0000

Data Index: 1255450 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1631. Min Act: -0.0000

Data Index: 23161 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1602. Min Act: -0.0000

Data Index: 826233 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1224184 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1649. Min Act: -0.0000

Data Index: 623501 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1639. Min Act: -0.0000

Data Index: 451863 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1570. Min Act: -0.0001

Data Index: 382818 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.1998. Min Range: -0.1998

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1297759 (C4 (Web Text))

Max Activating Token Index: 940