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

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

Neuron 1615 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.9447. Min Act: -0.0000

Data Index: 128934 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8337. Min Act: -0.0000

Data Index: 661872 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.9611. Min Act: -0.0000

Data Index: 815533 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1096489 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8616. Min Act: -0.0000

Data Index: 488664 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8743. Min Act: -0.0000

Data Index: 545544 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7887. Min Act: -0.0000

Data Index: 458536 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1111271 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7994. Min Act: -0.0000

Data Index: 686454 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1014769 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1254017 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7388. Min Act: -0.0000

Data Index: 238093 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.6946. Min Act: -0.0000

Data Index: 197777 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7149. Min Act: -0.0000

Data Index: 133972 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1230750 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.6970. Min Act: -0.0000

Data Index: 865854 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.6875. Min Act: -0.0000

Data Index: 435731 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7127. Min Act: -0.0000

Data Index: 122963 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1108735 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1153150 (C4 (Web Text))

Max Activating Token Index: 844