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

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

Neuron 2857 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: 0.0615. Min Range: -0.0615

Max Act: 0.0599. Min Act: -0.0002

Data Index: 387239 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0614. Min Act: -0.0002

Data Index: 280547 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0002

Data Index: 681295 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0613. Min Act: -0.0002

Data Index: 813770 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0583. Min Act: -0.0002

Data Index: 792725 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0558. Min Act: -0.0002

Data Index: 498269 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0557. Min Act: -0.0002

Data Index: 748967 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0543. Min Act: -0.0002

Data Index: 631949 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1133480 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1414453 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0523. Min Act: -0.0002

Data Index: 121167 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1313041 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0517. Min Act: -0.0002

Data Index: 608846 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0533. Min Act: -0.0002

Data Index: 690908 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0508. Min Act: -0.0002

Data Index: 441309 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0524. Min Act: -0.0002

Data Index: 870915 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0481. Min Act: -0.0002

Data Index: 197880 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0497. Min Act: -0.0002

Data Index: 329962 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0499. Min Act: -0.0002

Data Index: 804371 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0487. Min Act: -0.0002

Data Index: 668863 (C4 (Web Text))

Max Activating Token Index: 103