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

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

Neuron 5789 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: 0.0256. Min Range: -0.0256

Max Act: 0.0256. Min Act: -0.0001

Data Index: 836447 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0254. Min Act: -0.0001

Data Index: 61895 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0250. Min Act: -0.0001

Data Index: 321190 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1237909 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0239. Min Act: -0.0001

Data Index: 27162 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0237. Min Act: -0.0001

Data Index: 962883 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0236. Min Act: -0.0001

Data Index: 878825 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0232. Min Act: -0.0001

Data Index: 403914 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1039929 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0224. Min Act: -0.0001

Data Index: 221607 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0222. Min Act: -0.0002

Data Index: 745563 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0220. Min Act: -0.0001

Data Index: 596159 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0221. Min Act: -0.0001

Data Index: 615836 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0221. Min Act: -0.0001

Data Index: 248182 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0217. Min Act: -0.0001

Data Index: 924655 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0216. Min Act: -0.0001

Data Index: 946433 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1314624 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1093132 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0212. Min Act: -0.0001

Data Index: 159935 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0214. Min Act: -0.0001

Data Index: 877444 (C4 (Web Text))

Max Activating Token Index: 212