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

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

Neuron 4531 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: 0.0247. Min Range: -0.0247

Max Act: 0.0247. Min Act: -0.0001

Data Index: 887855 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0225. Min Act: -0.0001

Data Index: 350164 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0215. Min Act: -0.0001

Data Index: 931604 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0206. Min Act: -0.0001

Data Index: 924715 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0204. Min Act: -0.0001

Data Index: 58156 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1014786 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0198. Min Act: -0.0001

Data Index: 457868 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0198. Min Act: -0.0001

Data Index: 401210 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0191. Min Act: -0.0001

Data Index: 801697 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0189. Min Act: -0.0001

Data Index: 149943 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1266458 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0189. Min Act: -0.0001

Data Index: 793654 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0190. Min Act: -0.0001

Data Index: 892401 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0188. Min Act: -0.0001

Data Index: 403475 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0187. Min Act: -0.0001

Data Index: 821652 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1057087 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1289771 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0184. Min Act: -0.0001

Data Index: 708757 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0178. Min Act: -0.0001

Data Index: 188546 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0180. Min Act: -0.0001

Data Index: 642390 (C4 (Web Text))

Max Activating Token Index: 927