Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4552 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0001

Data Index: 378956 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1341512 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0298. Min Act: -0.0001

Data Index: 667766 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0338. Min Act: -0.0001

Data Index: 144355 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0243. Min Act: -0.0001

Data Index: 640004 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0188. Min Act: -0.0001

Data Index: 770280 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0211. Min Act: -0.0001

Data Index: 396740 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0250. Min Act: -0.0001

Data Index: 813046 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0225. Min Act: -0.0001

Data Index: 9556 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0252. Min Act: -0.0001

Data Index: 513882 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1177314 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0233. Min Act: -0.0001

Data Index: 327082 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0234. Min Act: -0.0001

Data Index: 287532 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0232. Min Act: -0.0001

Data Index: 794501 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0245. Min Act: -0.0001

Data Index: 261687 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0241. Min Act: -0.0001

Data Index: 773442 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1035240 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0221. Min Act: -0.0001

Data Index: 646799 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0213. Min Act: -0.0001

Data Index: 459065 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0216. Min Act: -0.0001

Data Index: 833811 (C4 (Web Text))

Max Activating Token Index: 396