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

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

Neuron 1888 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.7014. Min Act: -0.0000

Data Index: 823742 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.7238. Min Act: -0.0000

Data Index: 590542 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6768. Min Act: -0.0000

Data Index: 118463 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1336015 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6408. Min Act: -0.0000

Data Index: 160871 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6370. Min Act: -0.0000

Data Index: 290599 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5821. Min Act: -0.0000

Data Index: 351543 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.7125. Min Act: -0.0000

Data Index: 334595 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6477. Min Act: -0.0000

Data Index: 315350 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6271. Min Act: -0.0000

Data Index: 995517 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1017681 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1065883 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1033192 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6106. Min Act: -0.0000

Data Index: 114323 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1027306 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5517. Min Act: -0.0000

Data Index: 734106 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5238. Min Act: -0.0000

Data Index: 226377 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6169. Min Act: -0.0000

Data Index: 464156 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1269218 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1201606 (C4 (Web Text))

Max Activating Token Index: 288