Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 367 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1989. Min Act: -0.0002

Data Index: 516688 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1933. Min Act: -0.0001

Data Index: 1069140 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1761. Min Act: -0.0001

Data Index: 1345296 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1850. Min Act: -0.0001

Data Index: 491270 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1845. Min Act: -0.0002

Data Index: 1259505 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1672. Min Act: -0.0002

Data Index: 238495 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1675. Min Act: -0.0001

Data Index: 547095 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1670. Min Act: -0.0001

Data Index: 613460 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1702. Min Act: -0.0002

Data Index: 352727 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1056416 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1575. Min Act: -0.0002

Data Index: 1213144 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1614. Min Act: -0.0002

Data Index: 254021 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1581. Min Act: -0.0002

Data Index: 569403 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1620. Min Act: -0.0002

Data Index: 1233488 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1622. Min Act: -0.0002

Data Index: 1344553 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1525. Min Act: -0.0001

Data Index: 865787 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1579. Min Act: -0.0002

Data Index: 501404 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1279743 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1558. Min Act: -0.0001

Data Index: 483631 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1548. Min Act: -0.0002

Data Index: 651478 (C4 (Web Text))

Max Activating Token Index: 695