Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2914 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5857. Min Range: -2.5857

Max Act: 2.5857. Min Act: -0.0000

Data Index: 822023 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 2.5857. Min Range: -2.5857

Max Act: 2.3308. Min Act: -0.0000

Data Index: 971779 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 2.5857. Min Range: -2.5857

Max Act: 2.3046. Min Act: -0.0000

Data Index: 1146776 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 2.5857. Min Range: -2.5857

Max Act: 2.0602. Min Act: -0.0000

Data Index: 416438 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.9444. Min Act: -0.0000

Data Index: 388936 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 2.5857. Min Range: -2.5857

Max Act: 2.0214. Min Act: -0.0000

Data Index: 757737 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 2.5857. Min Range: -2.5857

Max Act: 2.0319. Min Act: -0.0000

Data Index: 1047791 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 2.5857. Min Range: -2.5857

Max Act: 2.1420. Min Act: -0.0000

Data Index: 1146524 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.9115. Min Act: -0.0000

Data Index: 616356 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.9077. Min Act: -0.0000

Data Index: 1271434 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 2.5857. Min Range: -2.5857

Max Act: 2.1156. Min Act: -0.0000

Data Index: 606030 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.9886. Min Act: -0.0000

Data Index: 131366 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.9883. Min Act: -0.0000

Data Index: 497371 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.7717. Min Act: -0.0000

Data Index: 640539 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.9655. Min Act: -0.0000

Data Index: 764947 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.8652. Min Act: -0.0000

Data Index: 855206 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.9173. Min Act: -0.0000

Data Index: 723857 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.8024. Min Act: -0.0000

Data Index: 1181611 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.8053. Min Act: -0.0000

Data Index: 742733 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 2.5857. Min Range: -2.5857

Max Act: 1.7847. Min Act: -0.0000

Data Index: 515168 (C4 (Web Text))

Max Activating Token Index: 767