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

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

Neuron 3704 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.5286. Min Act: -0.0000

Data Index: 529828 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.3590. Min Act: -0.0000

Data Index: 1225604 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.3627. Min Act: -0.0000

Data Index: 262576 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.2890. Min Act: -0.0000

Data Index: 383272 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.3763. Min Act: -0.0001

Data Index: 1162454 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1335745 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.1959. Min Act: -0.0000

Data Index: 193917 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.3115. Min Act: -0.0000

Data Index: 588769 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.2257. Min Act: -0.0000

Data Index: 516796 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1188311 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1215409 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.1025. Min Act: -0.0001

Data Index: 650291 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.2214. Min Act: -0.0000

Data Index: 782056 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.1476. Min Act: -0.0000

Data Index: 870414 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.1391. Min Act: -0.0000

Data Index: 640219 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.0613. Min Act: -0.0000

Data Index: 989264 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.1161. Min Act: -0.0001

Data Index: 114086 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.1228. Min Act: -0.0000

Data Index: 964486 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.1020. Min Act: -0.0000

Data Index: 793417 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.0757. Min Act: -0.0001

Data Index: 315198 (C4 (Web Text))

Max Activating Token Index: 311