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

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

Neuron 4087 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: 0.4147. Min Range: -0.4147

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1059126 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1290487 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3357. Min Act: -0.0000

Data Index: 814541 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3035. Min Act: -0.0000

Data Index: 21401 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1275987 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1195664 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2842. Min Act: 0.0000

Data Index: 50798 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2681. Min Act: -0.0000

Data Index: 146608 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2488. Min Act: -0.0000

Data Index: 912925 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2685. Min Act: -0.0000

Data Index: 397124 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1200667 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1245712 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2792. Min Act: -0.0000

Data Index: 370459 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2667. Min Act: -0.0000

Data Index: 330862 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2447. Min Act: -0.0000

Data Index: 80372 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2434. Min Act: -0.0000

Data Index: 417629 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2569. Min Act: -0.0000

Data Index: 520386 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2585. Min Act: -0.0000

Data Index: 891357 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2791. Min Act: -0.0000

Data Index: 835050 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2461. Min Act: -0.0000

Data Index: 732683 (C4 (Web Text))

Max Activating Token Index: 413