Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 323 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0719. Min Act: -0.0004

Data Index: 243365 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0004

Data Index: 118086 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0681. Min Act: -0.0004

Data Index: 505487 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0680. Min Act: -0.0004

Data Index: 1336769 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0661. Min Act: -0.0004

Data Index: 571530 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0661. Min Act: -0.0004

Data Index: 957114 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0550. Min Act: -0.0004

Data Index: 771288 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0668. Min Act: -0.0004

Data Index: 1109214 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0691. Min Act: -0.0004

Data Index: 552694 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0610. Min Act: -0.0004

Data Index: 557268 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0612. Min Act: -0.0004

Data Index: 745111 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0637. Min Act: -0.0004

Data Index: 377673 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0552. Min Act: -0.0004

Data Index: 467075 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0609. Min Act: -0.0004

Data Index: 1248012 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0603. Min Act: -0.0004

Data Index: 553541 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0579. Min Act: -0.0004

Data Index: 1075512 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0619. Min Act: -0.0004

Data Index: 583316 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0571. Min Act: -0.0004

Data Index: 1062953 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0574. Min Act: -0.0004

Data Index: 591576 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0549. Min Act: -0.0004

Data Index: 439379 (C4 (Web Text))

Max Activating Token Index: 922