Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2449 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1193296 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0370. Min Act: -0.0001

Data Index: 613790 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0327. Min Act: -0.0001

Data Index: 637833 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0307. Min Act: -0.0001

Data Index: 307392 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0292. Min Act: -0.0001

Data Index: 846166 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1212257 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0260. Min Act: -0.0001

Data Index: 55838 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1244455 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0282. Min Act: -0.0001

Data Index: 281950 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0248. Min Act: -0.0001

Data Index: 536074 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0273. Min Act: -0.0001

Data Index: 569077 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1384052 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0217. Min Act: -0.0001

Data Index: 229934 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0213. Min Act: -0.0001

Data Index: 41665 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0217. Min Act: -0.0001

Data Index: 918386 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1580182 (Python Code)

Max Activating Token Index: 1007

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0227. Min Act: -0.0001

Data Index: 14576 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1515832 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0208. Min Act: -0.0001

Data Index: 987182 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1537884 (Python Code)

Max Activating Token Index: 957