Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3060 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5723. Min Act: -0.0000

Data Index: 687321 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5506. Min Act: -0.0000

Data Index: 922288 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5498. Min Act: -0.0000

Data Index: 336914 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5307. Min Act: -0.0000

Data Index: 546904 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5465. Min Act: -0.0000

Data Index: 33530 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5071. Min Act: -0.0000

Data Index: 511202 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4937. Min Act: -0.0000

Data Index: 664599 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5108. Min Act: -0.0000

Data Index: 229268 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5058. Min Act: -0.0000

Data Index: 207367 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1050782 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5275. Min Act: -0.0000

Data Index: 556843 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1323698 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4661. Min Act: -0.0000

Data Index: 812725 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4992. Min Act: -0.0000

Data Index: 133487 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4660. Min Act: -0.0000

Data Index: 991123 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4929. Min Act: -0.0000

Data Index: 714522 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4636. Min Act: -0.0000

Data Index: 94589 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4766. Min Act: -0.0000

Data Index: 161501 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4696. Min Act: -0.0000

Data Index: 951756 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4813. Min Act: -0.0000

Data Index: 606391 (C4 (Web Text))

Max Activating Token Index: 885