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

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

Neuron 4252 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0003

Data Index: 602065 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0298. Min Act: -0.0003

Data Index: 43316 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0237. Min Act: -0.0003

Data Index: 398479 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1195293 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0232. Min Act: -0.0003

Data Index: 924239 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0217. Min Act: -0.0003

Data Index: 771331 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0217. Min Act: -0.0003

Data Index: 699880 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1125847 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0220. Min Act: -0.0003

Data Index: 355376 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1096098 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1269364 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0211. Min Act: -0.0003

Data Index: 155185 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0215. Min Act: -0.0003

Data Index: 526594 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0216. Min Act: -0.0003

Data Index: 939995 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0215. Min Act: -0.0003

Data Index: 542574 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1142845 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0206. Min Act: -0.0003

Data Index: 98531 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0210. Min Act: -0.0003

Data Index: 500581 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0207. Min Act: -0.0003

Data Index: 783123 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0202. Min Act: -0.0003

Data Index: 604699 (C4 (Web Text))

Max Activating Token Index: 189