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

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

Neuron 640 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6550. Min Act: -0.0001

Data Index: 168449 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6241. Min Act: -0.0001

Data Index: 238547 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6063. Min Act: -0.0001

Data Index: 749415 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5831. Min Act: -0.0001

Data Index: 810084 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5950. Min Act: -0.0001

Data Index: 56177 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5760. Min Act: -0.0001

Data Index: 297673 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5684. Min Act: -0.0001

Data Index: 305420 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5921. Min Act: -0.0001

Data Index: 1248915 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5962. Min Act: -0.0001

Data Index: 821756 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5479. Min Act: -0.0001

Data Index: 62653 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5905. Min Act: -0.0001

Data Index: 221331 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5908. Min Act: -0.0001

Data Index: 455473 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5403. Min Act: -0.0001

Data Index: 60842 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5282. Min Act: -0.0001

Data Index: 1122365 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5506. Min Act: -0.0001

Data Index: 1061119 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5616. Min Act: -0.0001

Data Index: 886516 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5756. Min Act: -0.0001

Data Index: 1029457 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5777. Min Act: -0.0001

Data Index: 606048 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5281. Min Act: -0.0001

Data Index: 183460 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5568. Min Act: -0.0001

Data Index: 542843 (C4 (Web Text))

Max Activating Token Index: 167