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

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

Neuron 2028 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3475. Min Act: -0.0000

Data Index: 625333 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3571. Min Act: -0.0000

Data Index: 387354 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3196. Min Act: -0.0000

Data Index: 665747 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3076. Min Act: -0.0000

Data Index: 49630 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1327785 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2995. Min Act: -0.0000

Data Index: 980268 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3002. Min Act: -0.0000

Data Index: 133761 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2896. Min Act: -0.0000

Data Index: 626017 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2971. Min Act: -0.0000

Data Index: 217565 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2872. Min Act: -0.0000

Data Index: 854240 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3041. Min Act: -0.0000

Data Index: 700663 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2919. Min Act: -0.0000

Data Index: 525330 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3005. Min Act: -0.0000

Data Index: 442400 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2888. Min Act: -0.0000

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2793. Min Act: -0.0000

Data Index: 570758 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2737. Min Act: -0.0000

Data Index: 33911 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2812. Min Act: -0.0000

Data Index: 576728 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2815. Min Act: -0.0000

Data Index: 517932 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1306940 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1242371 (C4 (Web Text))

Max Activating Token Index: 838