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

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

Neuron 1430 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: 0.6307. Min Range: -0.6307

Max Act: 0.6307. Min Act: -0.0001

Data Index: 233920 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5862. Min Act: -0.0001

Data Index: 307831 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5611. Min Act: -0.0001

Data Index: 606242 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5688. Min Act: -0.0001

Data Index: 1063470 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4692. Min Act: -0.0001

Data Index: 691734 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5207. Min Act: -0.0001

Data Index: 1123903 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4975. Min Act: -0.0001

Data Index: 1047078 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5216. Min Act: -0.0001

Data Index: 352186 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1056723 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4954. Min Act: -0.0001

Data Index: 1144447 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5005. Min Act: -0.0001

Data Index: 614509 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4451. Min Act: -0.0001

Data Index: 737298 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4595. Min Act: -0.0001

Data Index: 626234 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4830. Min Act: -0.0001

Data Index: 27923 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5102. Min Act: -0.0001

Data Index: 29377 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4891. Min Act: -0.0001

Data Index: 633222 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5098. Min Act: -0.0001

Data Index: 1228603 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4592. Min Act: -0.0001

Data Index: 656577 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4469. Min Act: -0.0001

Data Index: 473035 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4365. Min Act: -0.0001

Data Index: 597411 (C4 (Web Text))

Max Activating Token Index: 305