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

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

Neuron 1325 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6287. Min Act: -0.0001

Data Index: 23919 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6772. Min Act: -0.0001

Data Index: 235156 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5794. Min Act: -0.0001

Data Index: 614429 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5853. Min Act: -0.0001

Data Index: 173210 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5697. Min Act: -0.0001

Data Index: 330894 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5877. Min Act: -0.0001

Data Index: 677590 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6018. Min Act: -0.0001

Data Index: 138265 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5568. Min Act: -0.0001

Data Index: 477465 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5582. Min Act: -0.0001

Data Index: 463878 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5715. Min Act: -0.0001

Data Index: 1070823 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5695. Min Act: -0.0001

Data Index: 248166 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5672. Min Act: -0.0001

Data Index: 719929 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5317. Min Act: -0.0001

Data Index: 288299 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5663. Min Act: -0.0001

Data Index: 1306977 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5151. Min Act: -0.0001

Data Index: 1031770 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5551. Min Act: -0.0001

Data Index: 229076 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5340. Min Act: -0.0001

Data Index: 905386 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5040. Min Act: -0.0001

Data Index: 945517 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5739. Min Act: -0.0001

Data Index: 1240666 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5552. Min Act: -0.0001

Data Index: 704118 (C4 (Web Text))

Max Activating Token Index: 580