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

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

Neuron 937 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: 0.3772. Min Range: -0.3772

Max Act: 0.3448. Min Act: -0.0001

Data Index: 174466 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3772. Min Act: -0.0001

Data Index: 472087 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2973. Min Act: -0.0001

Data Index: 27205 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2923. Min Act: -0.0001

Data Index: 652150 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3092. Min Act: -0.0001

Data Index: 248735 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2936. Min Act: -0.0001

Data Index: 61978 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2891. Min Act: -0.0001

Data Index: 1166540 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2807. Min Act: -0.0001

Data Index: 798037 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2883. Min Act: -0.0001

Data Index: 193283 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2513. Min Act: -0.0001

Data Index: 716535 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2640. Min Act: -0.0001

Data Index: 334792 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2955. Min Act: -0.0001

Data Index: 1246489 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2816. Min Act: -0.0001

Data Index: 918926 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2729. Min Act: -0.0001

Data Index: 955474 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2789. Min Act: -0.0001

Data Index: 84692 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2674. Min Act: -0.0001

Data Index: 32810 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2937. Min Act: -0.0001

Data Index: 862242 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2707. Min Act: -0.0001

Data Index: 655901 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2615. Min Act: -0.0001

Data Index: 1228244 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2817. Min Act: -0.0001

Data Index: 277776 (C4 (Web Text))

Max Activating Token Index: 575