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

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

Neuron 5407 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: 0.0615. Min Act: -0.0002

Data Index: 496157 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1161493 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0609. Min Act: -0.0002

Data Index: 264174 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0597. Min Act: -0.0002

Data Index: 516365 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0590. Min Act: -0.0002

Data Index: 976053 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0566. Min Act: -0.0002

Data Index: 103598 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1166466 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0583. Min Act: -0.0002

Data Index: 363503 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0602. Min Act: -0.0002

Data Index: 381017 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1407604 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0543. Min Act: -0.0002

Data Index: 985053 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0575. Min Act: -0.0002

Data Index: 785084 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0531. Min Act: -0.0002

Data Index: 304992 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0526. Min Act: -0.0002

Data Index: 399653 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0580. Min Act: -0.0002

Data Index: 93018 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0554. Min Act: -0.0002

Data Index: 691928 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0543. Min Act: -0.0002

Data Index: 735271 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0505. Min Act: -0.0002

Data Index: 476925 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0520. Min Act: -0.0002

Data Index: 854066 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0519. Min Act: -0.0002

Data Index: 620227 (C4 (Web Text))

Max Activating Token Index: 69