Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1179 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0003

Data Index: 297783 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0748. Min Act: -0.0003

Data Index: 40906 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0707. Min Act: -0.0003

Data Index: 569981 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0746. Min Act: -0.0004

Data Index: 1156724 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0709. Min Act: -0.0004

Data Index: 290439 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0698. Min Act: -0.0004

Data Index: 38939 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0671. Min Act: -0.0003

Data Index: 703410 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0674. Min Act: -0.0004

Data Index: 1019076 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0676. Min Act: -0.0003

Data Index: 535076 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0657. Min Act: -0.0003

Data Index: 795229 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0676. Min Act: -0.0003

Data Index: 863711 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1236957 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0658. Min Act: -0.0004

Data Index: 1067416 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0673. Min Act: -0.0003

Data Index: 40266 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1328989 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0638. Min Act: -0.0003

Data Index: 777136 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1137218 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0639. Min Act: -0.0003

Data Index: 544538 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0649. Min Act: -0.0003

Data Index: 409374 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0644. Min Act: -0.0004

Data Index: 689204 (C4 (Web Text))

Max Activating Token Index: 564