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

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

Neuron 1669 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: 0.0523. Min Range: -0.0523

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1447713 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0511. Min Act: -0.0003

Data Index: 497223 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0508. Min Act: -0.0003

Data Index: 660276 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0004

Data Index: 767911 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0506. Min Act: -0.0003

Data Index: 772664 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0484. Min Act: -0.0003

Data Index: 741101 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0498. Min Act: -0.0003

Data Index: 89795 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1453103 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1308678 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1012775 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0481. Min Act: -0.0004

Data Index: 671852 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0465. Min Act: -0.0003

Data Index: 261248 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1443468 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0471. Min Act: -0.0003

Data Index: 666117 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1058123 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0471. Min Act: -0.0003

Data Index: 895569 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0453. Min Act: -0.0003

Data Index: 574066 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0458. Min Act: -0.0004

Data Index: 1293420 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1050484 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0454. Min Act: -0.0003

Data Index: 602977 (C4 (Web Text))

Max Activating Token Index: 163