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

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

Neuron 51 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: 0.2689. Min Range: -0.2689

Max Act: 0.2689. Min Act: -0.0004

Data Index: 1384211 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2499. Min Act: -0.0004

Data Index: 1628658 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2310. Min Act: -0.0004

Data Index: 1423398 (Python Code)

Max Activating Token Index: 705

Text #3

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2389. Min Act: -0.0004

Data Index: 1630477 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2552. Min Act: -0.0004

Data Index: 1500260 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2359. Min Act: -0.0004

Data Index: 1479290 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2361. Min Act: -0.0004

Data Index: 1425364 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2382. Min Act: -0.0004

Data Index: 1436541 (Python Code)

Max Activating Token Index: 178

Text #8

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2304. Min Act: -0.0004

Data Index: 1435412 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2287. Min Act: -0.0004

Data Index: 1544561 (Python Code)

Max Activating Token Index: 314

Text #10

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2279. Min Act: -0.0004

Data Index: 1392024 (Python Code)

Max Activating Token Index: 1000

Text #11

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2363. Min Act: -0.0004

Data Index: 1464244 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2337. Min Act: -0.0004

Data Index: 1536907 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2245. Min Act: -0.0004

Data Index: 1447629 (Python Code)

Max Activating Token Index: 287

Text #14

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2230. Min Act: -0.0004

Data Index: 1625439 (Python Code)

Max Activating Token Index: 266

Text #15

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2216. Min Act: -0.0004

Data Index: 1443415 (Python Code)

Max Activating Token Index: 358

Text #16

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2221. Min Act: -0.0004

Data Index: 1492762 (Python Code)

Max Activating Token Index: 957

Text #17

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2226. Min Act: -0.0004

Data Index: 1606016 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2303. Min Act: -0.0004

Data Index: 1480897 (Python Code)

Max Activating Token Index: 980

Text #19

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2297. Min Act: -0.0004

Data Index: 1532032 (Python Code)

Max Activating Token Index: 432