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

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

Neuron 3261 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: 0.3234. Min Range: -0.3234

Max Act: 0.3234. Min Act: -0.0001

Data Index: 1381839 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2603. Min Act: -0.0001

Data Index: 1472778 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2682. Min Act: -0.0001

Data Index: 1653440 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2571. Min Act: -0.0001

Data Index: 1362315 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2561. Min Act: -0.0001

Data Index: 1588735 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2503. Min Act: -0.0001

Data Index: 1638663 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1610507 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2432. Min Act: -0.0001

Data Index: 1401448 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1480888 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1407485 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2372. Min Act: -0.0001

Data Index: 1463937 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2386. Min Act: -0.0001

Data Index: 1511575 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2299. Min Act: -0.0001

Data Index: 1420255 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1420031 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2293. Min Act: -0.0001

Data Index: 1639288 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1540805 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2293. Min Act: -0.0001

Data Index: 1646901 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2283. Min Act: -0.0001

Data Index: 1491062 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2286. Min Act: -0.0001

Data Index: 1557149 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2278. Min Act: -0.0001

Data Index: 1452262 (Python Code)

Max Activating Token Index: 1023