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

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

Neuron 2592 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1262917 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0985. Min Act: -0.0001

Data Index: 271381 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0738. Min Act: -0.0001

Data Index: 935254 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0757. Min Act: -0.0001

Data Index: 545519 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1296516 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0738. Min Act: -0.0001

Data Index: 812150 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0723. Min Act: -0.0001

Data Index: 775471 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0687. Min Act: -0.0001

Data Index: 654064 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0676. Min Act: -0.0001

Data Index: 950619 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0635. Min Act: -0.0001

Data Index: 112527 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0649. Min Act: -0.0001

Data Index: 647562 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0635. Min Act: -0.0001

Data Index: 532913 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0635. Min Act: -0.0001

Data Index: 96510 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1085511 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0656. Min Act: -0.0001

Data Index: 664134 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0570. Min Act: -0.0001

Data Index: 513704 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0602. Min Act: -0.0001

Data Index: 35723 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1205767 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0627. Min Act: -0.0001

Data Index: 766407 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0610. Min Act: -0.0001

Data Index: 307359 (C4 (Web Text))

Max Activating Token Index: 542