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

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

Neuron 149 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0337. Min Act: -0.0006

Data Index: 808455 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0281. Min Act: -0.0006

Data Index: 960678 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0271. Min Act: -0.0006

Data Index: 394131 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0257. Min Act: -0.0006

Data Index: 659629 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0262. Min Act: -0.0006

Data Index: 611492 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1120857 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0247. Min Act: -0.0006

Data Index: 254708 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1062007 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1289814 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1206776 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1210312 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0243. Min Act: -0.0006

Data Index: 242646 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0247. Min Act: -0.0006

Data Index: 709537 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1336856 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0233. Min Act: -0.0006

Data Index: 944731 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0233. Min Act: -0.0006

Data Index: 911546 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0236. Min Act: -0.0006

Data Index: 93729 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0224. Min Act: -0.0006

Data Index: 692742 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0235. Min Act: -0.0006

Data Index: 16648 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0223. Min Act: -0.0006

Data Index: 286478 (C4 (Web Text))

Max Activating Token Index: 347