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

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

Neuron 4754 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: 0.1437. Min Range: -0.1437

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1046915 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1236. Min Act: -0.0001

Data Index: 464975 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1246. Min Act: -0.0001

Data Index: 993251 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1246. Min Act: -0.0001

Data Index: 356731 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1225. Min Act: -0.0001

Data Index: 676259 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1219. Min Act: -0.0001

Data Index: 263819 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1232. Min Act: -0.0001

Data Index: 159842 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1187. Min Act: -0.0001

Data Index: 328312 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1217. Min Act: -0.0001

Data Index: 66904 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1182. Min Act: -0.0001

Data Index: 370419 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1201. Min Act: -0.0001

Data Index: 464429 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1217. Min Act: -0.0001

Data Index: 576098 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1105369 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1176. Min Act: -0.0001

Data Index: 696160 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1160. Min Act: -0.0001

Data Index: 35388 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1188. Min Act: -0.0001

Data Index: 424078 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1178. Min Act: -0.0001

Data Index: 812041 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1164. Min Act: -0.0001

Data Index: 359510 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1180. Min Act: -0.0001

Data Index: 496057 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1146. Min Act: -0.0001

Data Index: 7862 (C4 (Web Text))

Max Activating Token Index: 191