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

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

Neuron 4443 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.2092. Min Act: -0.0000

Data Index: 865533 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0934. Min Act: -0.0000

Data Index: 310075 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1134183 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9768. Min Act: -0.0000

Data Index: 685612 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9158. Min Act: -0.0000

Data Index: 13542 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1193363 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0158. Min Act: -0.0000

Data Index: 467424 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9705. Min Act: -0.0000

Data Index: 425443 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1272918 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9267. Min Act: -0.0000

Data Index: 704861 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1080934 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9213. Min Act: -0.0000

Data Index: 563164 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1164484 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9299. Min Act: -0.0000

Data Index: 6418 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8698. Min Act: -0.0000

Data Index: 494219 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8570. Min Act: -0.0000

Data Index: 777754 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8537. Min Act: -0.0000

Data Index: 276657 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8134. Min Act: -0.0000

Data Index: 986547 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8630. Min Act: -0.0000

Data Index: 317848 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.8265. Min Act: -0.0000

Data Index: 199165 (C4 (Web Text))

Max Activating Token Index: 234