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

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

Neuron 1961 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0006

Data Index: 1045424 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0585. Min Act: -0.0006

Data Index: 263146 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0583. Min Act: -0.0006

Data Index: 690772 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0575. Min Act: -0.0006

Data Index: 808320 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0553. Min Act: -0.0006

Data Index: 1125881 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0537. Min Act: -0.0006

Data Index: 313334 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0538. Min Act: -0.0006

Data Index: 994803 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0539. Min Act: -0.0006

Data Index: 1229866 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0544. Min Act: -0.0006

Data Index: 948179 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0513. Min Act: -0.0006

Data Index: 558779 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0517. Min Act: -0.0006

Data Index: 806238 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0496. Min Act: -0.0006

Data Index: 1090624 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0513. Min Act: -0.0006

Data Index: 1124801 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0486. Min Act: -0.0006

Data Index: 369415 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0503. Min Act: -0.0006

Data Index: 156224 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0485. Min Act: -0.0006

Data Index: 399256 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0512. Min Act: -0.0006

Data Index: 1122304 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0492. Min Act: -0.0006

Data Index: 1017332 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0490. Min Act: -0.0006

Data Index: 582834 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0488. Min Act: -0.0006

Data Index: 874923 (C4 (Web Text))

Max Activating Token Index: 262