Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2170 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0004

Data Index: 1163212 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0287. Min Act: -0.0004

Data Index: 1277221 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0293. Min Act: -0.0004

Data Index: 567458 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0286. Min Act: -0.0004

Data Index: 602169 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0273. Min Act: -0.0004

Data Index: 1585749 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1137508 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0282. Min Act: -0.0004

Data Index: 157824 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0256. Min Act: -0.0004

Data Index: 1093647 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1218394 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0295. Min Act: -0.0004

Data Index: 758716 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0261. Min Act: -0.0004

Data Index: 502676 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0251. Min Act: -0.0004

Data Index: 173981 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0280. Min Act: -0.0004

Data Index: 1644751 (Python Code)

Max Activating Token Index: 415

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0256. Min Act: -0.0004

Data Index: 597278 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0271. Min Act: -0.0004

Data Index: 425598 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0249. Min Act: -0.0004

Data Index: 1133101 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0252. Min Act: -0.0004

Data Index: 466780 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0251. Min Act: -0.0004

Data Index: 926710 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0259. Min Act: -0.0004

Data Index: 188420 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0241. Min Act: -0.0004

Data Index: 522647 (C4 (Web Text))

Max Activating Token Index: 342