Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 517 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0577. Min Act: -0.0003

Data Index: 25660 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0646. Min Act: -0.0003

Data Index: 374420 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0693. Min Act: -0.0003

Data Index: 670663 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1181365 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0630. Min Act: -0.0003

Data Index: 876545 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1139280 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0561. Min Act: -0.0003

Data Index: 585466 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1290394 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0523. Min Act: -0.0003

Data Index: 474961 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0003

Data Index: 900450 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0619. Min Act: -0.0003

Data Index: 878205 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0583. Min Act: -0.0003

Data Index: 864708 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0633. Min Act: -0.0004

Data Index: 204088 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0647. Min Act: -0.0003

Data Index: 481096 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1262595 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0551. Min Act: -0.0003

Data Index: 983658 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0478. Min Act: -0.0003

Data Index: 48074 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1096533 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1153542 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0576. Min Act: -0.0003

Data Index: 464137 (C4 (Web Text))

Max Activating Token Index: 601