Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1024 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0006

Data Index: 192826 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0254. Min Act: -0.0006

Data Index: 70612 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0252. Min Act: -0.0006

Data Index: 465624 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1049434 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1154726 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0242. Min Act: -0.0006

Data Index: 171173 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0237. Min Act: -0.0006

Data Index: 336953 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1043492 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1243573 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0238. Min Act: -0.0006

Data Index: 319330 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0232. Min Act: -0.0006

Data Index: 442719 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0237. Min Act: -0.0006

Data Index: 998588 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0231. Min Act: -0.0006

Data Index: 746610 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1025771 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0237. Min Act: -0.0006

Data Index: 939673 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0236. Min Act: -0.0006

Data Index: 418000 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0236. Min Act: -0.0006

Data Index: 232664 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0241. Min Act: -0.0006

Data Index: 691502 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1347030 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0235. Min Act: -0.0006

Data Index: 65561 (C4 (Web Text))

Max Activating Token Index: 663