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

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

Neuron 4508 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: 0.0263. Min Range: -0.0263

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1392219 (Python Code)

Max Activating Token Index: 408

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1433742 (Python Code)

Max Activating Token Index: 434

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1391658 (Python Code)

Max Activating Token Index: 574

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1560711 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1535792 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1361771 (Python Code)

Max Activating Token Index: 233

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1564106 (Python Code)

Max Activating Token Index: 996

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1438340 (Python Code)

Max Activating Token Index: 681

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1420012 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1618985 (Python Code)

Max Activating Token Index: 997

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1555327 (Python Code)

Max Activating Token Index: 641

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0244. Min Act: -0.0001

Data Index: 1548842 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1524193 (Python Code)

Max Activating Token Index: 465

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1637003 (Python Code)

Max Activating Token Index: 540

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1563082 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1403309 (Python Code)

Max Activating Token Index: 647

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1443534 (Python Code)

Max Activating Token Index: 327

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1540679 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1531169 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1520952 (Python Code)

Max Activating Token Index: 332