Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2723 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.5195. Min Act: -0.0001

Data Index: 533350 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4635. Min Act: -0.0001

Data Index: 76405 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4195. Min Act: -0.0001

Data Index: 40055 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4569. Min Act: -0.0001

Data Index: 459841 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4229. Min Act: -0.0001

Data Index: 42818 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.3216. Min Act: -0.0001

Data Index: 435396 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.3563. Min Act: -0.0001

Data Index: 1325362 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.3479. Min Act: -0.0001

Data Index: 1146673 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.2497. Min Act: -0.0001

Data Index: 1384223 (Python Code)

Max Activating Token Index: 432

Text #9

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.2556. Min Act: -0.0001

Data Index: 1135535 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.1683. Min Act: -0.0001

Data Index: 983943 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.2490. Min Act: -0.0001

Data Index: 593631 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.1726. Min Act: -0.0001

Data Index: 519945 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.2964. Min Act: -0.0001

Data Index: 444252 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.2202. Min Act: -0.0001

Data Index: 452819 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.1841. Min Act: -0.0001

Data Index: 458307 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.1562. Min Act: -0.0001

Data Index: 1078906 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.2344. Min Act: -0.0001

Data Index: 605830 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.1990. Min Act: -0.0001

Data Index: 945086 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.1047. Min Act: -0.0001

Data Index: 817566 (C4 (Web Text))

Max Activating Token Index: 894