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

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

Neuron 1570 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0314. Min Act: -0.0002

Data Index: 877410 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0317. Min Act: -0.0002

Data Index: 766973 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0361. Min Act: -0.0002

Data Index: 246861 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0337. Min Act: -0.0002

Data Index: 62261 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1626741 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0243. Min Act: -0.0002

Data Index: 944843 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0244. Min Act: -0.0002

Data Index: 653772 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0239. Min Act: -0.0002

Data Index: 992962 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1648143 (Python Code)

Max Activating Token Index: 909

Text #9

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0220. Min Act: -0.0002

Data Index: 968503 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1005603 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0182. Min Act: -0.0002

Data Index: 200798 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0197. Min Act: -0.0002

Data Index: 127909 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1259232 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0215. Min Act: -0.0002

Data Index: 371767 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0187. Min Act: -0.0002

Data Index: 976061 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0186. Min Act: -0.0002

Data Index: 767356 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0195. Min Act: -0.0002

Data Index: 924601 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0191. Min Act: -0.0002

Data Index: 939135 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0191. Min Act: -0.0002

Data Index: 510112 (C4 (Web Text))

Max Activating Token Index: 518