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

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

Neuron 3941 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3687. Min Act: -0.0000

Data Index: 498090 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3490. Min Act: -0.0000

Data Index: 118672 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3291. Min Act: -0.0000

Data Index: 632575 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3184. Min Act: -0.0000

Data Index: 511162 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3131. Min Act: -0.0000

Data Index: 940851 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2904. Min Act: -0.0000

Data Index: 808058 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3112. Min Act: -0.0000

Data Index: 230945 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1043181 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3000. Min Act: -0.0000

Data Index: 803791 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2904. Min Act: -0.0001

Data Index: 1595301 (Python Code)

Max Activating Token Index: 31

Text #10

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3027. Min Act: -0.0000

Data Index: 112418 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2888. Min Act: -0.0000

Data Index: 342791 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1017855 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2829. Min Act: -0.0000

Data Index: 87117 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1011284 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2792. Min Act: -0.0000

Data Index: 161284 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2748. Min Act: -0.0000

Data Index: 651076 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2470. Min Act: -0.0000

Data Index: 171290 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1134828 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1174561 (C4 (Web Text))

Max Activating Token Index: 494