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

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

Neuron 1096 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: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0002

Data Index: 712156 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0659. Min Act: -0.0002

Data Index: 957910 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1069234 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0622. Min Act: -0.0002

Data Index: 254018 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0636. Min Act: -0.0002

Data Index: 621255 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0616. Min Act: -0.0001

Data Index: 22064 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0619. Min Act: -0.0001

Data Index: 397733 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0621. Min Act: -0.0002

Data Index: 230277 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0609. Min Act: 0.0001

Data Index: 722544 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0582. Min Act: -0.0001

Data Index: 775372 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0579. Min Act: -0.0000

Data Index: 878226 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0591. Min Act: -0.0002

Data Index: 930132 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0576. Min Act: -0.0002

Data Index: 175043 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0581. Min Act: -0.0002

Data Index: 454797 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0580. Min Act: -0.0001

Data Index: 262883 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0587. Min Act: -0.0002

Data Index: 660392 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0577. Min Act: 0.0001

Data Index: 713909 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1188580 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0567. Min Act: -0.0000

Data Index: 112330 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1072758 (C4 (Web Text))

Max Activating Token Index: 146