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

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

Neuron 5432 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.7142. Min Act: -0.0000

Data Index: 664948 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6588. Min Act: -0.0000

Data Index: 649948 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1118615 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6948. Min Act: -0.0000

Data Index: 544506 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1111499 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.7261. Min Act: -0.0000

Data Index: 548988 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6370. Min Act: -0.0000

Data Index: 469295 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6627. Min Act: -0.0000

Data Index: 493976 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6611. Min Act: -0.0000

Data Index: 501306 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6765. Min Act: -0.0000

Data Index: 406277 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6533. Min Act: -0.0000

Data Index: 365483 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6204. Min Act: -0.0000

Data Index: 424749 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6531. Min Act: -0.0000

Data Index: 27386 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1350447 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1316413 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6113. Min Act: -0.0000

Data Index: 828935 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1236208 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1141822 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1000655 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.7352. Min Range: -0.7352

Max Act: 0.6259. Min Act: -0.0000

Data Index: 865076 (C4 (Web Text))

Max Activating Token Index: 146