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

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

Neuron 1592 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: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0003

Data Index: 575406 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0678. Min Act: -0.0003

Data Index: 498208 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1034526 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0642. Min Act: -0.0003

Data Index: 706847 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1226001 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0635. Min Act: -0.0002

Data Index: 975868 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0600. Min Act: -0.0003

Data Index: 96129 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0617. Min Act: -0.0003

Data Index: 803043 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0593. Min Act: -0.0003

Data Index: 383975 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0603. Min Act: -0.0004

Data Index: 595436 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1338619 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0579. Min Act: -0.0004

Data Index: 676671 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0596. Min Act: -0.0003

Data Index: 682367 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0569. Min Act: -0.0003

Data Index: 717232 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0591. Min Act: -0.0003

Data Index: 545284 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0574. Min Act: -0.0003

Data Index: 933511 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0573. Min Act: -0.0003

Data Index: 211482 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0560. Min Act: -0.0003

Data Index: 697390 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1116578 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0552. Min Act: -0.0004

Data Index: 575747 (C4 (Web Text))

Max Activating Token Index: 166