Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1980 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0569. Min Act: -0.0003

Data Index: 924676 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1485508 (Python Code)

Max Activating Token Index: 744

Text #2

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0470. Min Act: -0.0003

Data Index: 249690 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1116004 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0441. Min Act: -0.0003

Data Index: 471120 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1155995 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0444. Min Act: -0.0003

Data Index: 172670 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0433. Min Act: -0.0003

Data Index: 583699 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0433. Min Act: -0.0002

Data Index: 458115 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1198419 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0429. Min Act: -0.0003

Data Index: 635923 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0434. Min Act: -0.0003

Data Index: 866403 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0403. Min Act: -0.0003

Data Index: 875414 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1381866 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0433. Min Act: -0.0003

Data Index: 548452 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0417. Min Act: -0.0003

Data Index: 112571 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0424. Min Act: -0.0002

Data Index: 345374 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0424. Min Act: -0.0003

Data Index: 773565 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0427. Min Act: -0.0003

Data Index: 833682 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0415. Min Act: -0.0003

Data Index: 347013 (C4 (Web Text))

Max Activating Token Index: 115