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

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

Neuron 5435 in Layer 1

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: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0002

Data Index: 1174241 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1458. Min Act: -0.0002

Data Index: 682797 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1423. Min Act: -0.0002

Data Index: 46635 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1360. Min Act: -0.0002

Data Index: 722168 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1366. Min Act: -0.0002

Data Index: 489993 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1336. Min Act: -0.0002

Data Index: 824369 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1320. Min Act: -0.0002

Data Index: 1060103 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1294. Min Act: -0.0002

Data Index: 15124 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1268. Min Act: -0.0002

Data Index: 554176 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1246. Min Act: -0.0002

Data Index: 1278710 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1235. Min Act: -0.0002

Data Index: 1146512 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1215. Min Act: -0.0002

Data Index: 450971 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1199. Min Act: -0.0002

Data Index: 369829 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1212. Min Act: -0.0002

Data Index: 388179 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1202. Min Act: -0.0002

Data Index: 983760 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1207. Min Act: -0.0002

Data Index: 439098 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1197. Min Act: -0.0002

Data Index: 839063 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1267460 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1202. Min Act: -0.0002

Data Index: 760465 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1216. Min Act: -0.0002

Data Index: 289336 (C4 (Web Text))

Max Activating Token Index: 784