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

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

Neuron 1244 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: 0.0679. Min Range: -0.0679

Max Act: 0.0679. Min Act: -0.0003

Data Index: 543200 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0658. Min Act: -0.0003

Data Index: 374586 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0645. Min Act: -0.0003

Data Index: 966910 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0588. Min Act: -0.0003

Data Index: 82503 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0603. Min Act: -0.0003

Data Index: 77841 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0582. Min Act: -0.0004

Data Index: 961084 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0570. Min Act: -0.0003

Data Index: 745286 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0590. Min Act: -0.0003

Data Index: 288598 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0582. Min Act: -0.0003

Data Index: 451861 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0574. Min Act: -0.0004

Data Index: 115229 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1224221 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0522. Min Act: -0.0003

Data Index: 229929 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0556. Min Act: -0.0003

Data Index: 598867 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0569. Min Act: -0.0003

Data Index: 611392 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0566. Min Act: -0.0004

Data Index: 385112 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0544. Min Act: -0.0003

Data Index: 537564 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0549. Min Act: -0.0003

Data Index: 45055 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0565. Min Act: -0.0003

Data Index: 341073 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0561. Min Act: -0.0003

Data Index: 899409 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0525. Min Act: -0.0003

Data Index: 309738 (C4 (Web Text))

Max Activating Token Index: 312