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

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

Neuron 3193 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1355049 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1116020 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0252. Min Act: -0.0002

Data Index: 975678 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0237. Min Act: -0.0002

Data Index: 499051 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1511986 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1147856 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1576232 (Python Code)

Max Activating Token Index: 882

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0210. Min Act: -0.0002

Data Index: 752837 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1407492 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1601441 (Python Code)

Max Activating Token Index: 730

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0201. Min Act: -0.0002

Data Index: 548701 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0205. Min Act: -0.0002

Data Index: 215232 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1243028 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0201. Min Act: -0.0002

Data Index: 483817 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1119546 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1273390 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1581808 (Python Code)

Max Activating Token Index: 466

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0191. Min Act: -0.0002

Data Index: 91420 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1263393 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1445455 (Python Code)

Max Activating Token Index: 544