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

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

Neuron 5696 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1029005 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0250. Min Act: -0.0001

Data Index: 508556 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0242. Min Act: -0.0001

Data Index: 18531 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1205560 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1627713 (Python Code)

Max Activating Token Index: 39

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0234. Min Act: -0.0001

Data Index: 820777 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1073457 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1635764 (Python Code)

Max Activating Token Index: 530

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0225. Min Act: -0.0001

Data Index: 405087 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0222. Min Act: -0.0001

Data Index: 665436 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0224. Min Act: -0.0001

Data Index: 897516 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0219. Min Act: -0.0001

Data Index: 666331 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1512566 (Python Code)

Max Activating Token Index: 726

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0219. Min Act: -0.0001

Data Index: 983686 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1479469 (Python Code)

Max Activating Token Index: 418

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0215. Min Act: -0.0001

Data Index: 373271 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0219. Min Act: -0.0001

Data Index: 398227 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0214. Min Act: -0.0001

Data Index: 286396 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1122731 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0215. Min Act: -0.0001

Data Index: 134427 (C4 (Web Text))

Max Activating Token Index: 378