Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1726 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1100227 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0734. Min Act: -0.0002

Data Index: 852311 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0701. Min Act: -0.0002

Data Index: 557158 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0658. Min Act: -0.0002

Data Index: 497379 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0656. Min Act: -0.0002

Data Index: 229334 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0641. Min Act: -0.0002

Data Index: 98465 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0636. Min Act: -0.0002

Data Index: 648470 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0618. Min Act: -0.0002

Data Index: 296625 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0613. Min Act: -0.0002

Data Index: 181504 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0636. Min Act: -0.0002

Data Index: 734572 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0609. Min Act: -0.0002

Data Index: 807671 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1207862 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0605. Min Act: -0.0002

Data Index: 543842 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0582. Min Act: -0.0002

Data Index: 894256 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1252905 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1105397 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1342858 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1304884 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0584. Min Act: -0.0002

Data Index: 407155 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0561. Min Act: -0.0002

Data Index: 32443 (C4 (Web Text))

Max Activating Token Index: 623