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

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

Neuron 4653 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7752. Min Range: -2.7752

Max Act: 2.7752. Min Act: -0.0000

Data Index: 183879 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 2.7752. Min Range: -2.7752

Max Act: 2.3184. Min Act: -0.0000

Data Index: 596772 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 2.7752. Min Range: -2.7752

Max Act: 2.3013. Min Act: -0.0000

Data Index: 926121 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 2.7752. Min Range: -2.7752

Max Act: 2.1069. Min Act: -0.0000

Data Index: 82501 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.9675. Min Act: -0.0000

Data Index: 1112773 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.9687. Min Act: -0.0000

Data Index: 47254 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.9120. Min Act: -0.0000

Data Index: 295482 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.7924. Min Act: -0.0000

Data Index: 1049021 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.8692. Min Act: -0.0000

Data Index: 132399 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.9387. Min Act: -0.0000

Data Index: 918879 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.9131. Min Act: -0.0000

Data Index: 382391 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.8122. Min Act: -0.0000

Data Index: 165440 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1277776 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.6264. Min Act: -0.0000

Data Index: 566470 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.7479. Min Act: -0.0000

Data Index: 641862 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.6369. Min Act: -0.0000

Data Index: 519818 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.8153. Min Act: -0.0000

Data Index: 1070975 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.5203. Min Act: -0.0000

Data Index: 1182831 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.6573. Min Act: -0.0000

Data Index: 1175870 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 2.7752. Min Range: -2.7752

Max Act: 1.6446. Min Act: -0.0000

Data Index: 1234635 (C4 (Web Text))

Max Activating Token Index: 642