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

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

Neuron 2909 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: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0004

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0356. Min Act: -0.0004

Data Index: 308975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0320. Min Act: -0.0004

Data Index: 831542 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0287. Min Act: -0.0004

Data Index: 1655344 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0307. Min Act: -0.0004

Data Index: 481203 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0317. Min Act: -0.0004

Data Index: 488797 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0285. Min Act: -0.0004

Data Index: 964915 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0300. Min Act: -0.0004

Data Index: 616997 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0300. Min Act: -0.0004

Data Index: 995631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0305. Min Act: -0.0004

Data Index: 1407282 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0298. Min Act: -0.0004

Data Index: 386552 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0309. Min Act: -0.0004

Data Index: 1423570 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0282. Min Act: -0.0004

Data Index: 1639106 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0271. Min Act: -0.0004

Data Index: 1476725 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1051875 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1169526 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0298. Min Act: -0.0004

Data Index: 389210 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0263. Min Act: -0.0004

Data Index: 751132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0246. Min Act: -0.0004

Data Index: 594721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0263. Min Act: -0.0004

Data Index: 1331007 (C4 (Web Text))

Max Activating Token Index: 948