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

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

Neuron 1641 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: 0.0229. Min Range: -0.0229

Max Act: 0.0229. Min Act: -0.0001

Data Index: 82794 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0217. Min Act: -0.0001

Data Index: 775656 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1258382 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1168285 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0205. Min Act: -0.0001

Data Index: 821476 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0205. Min Act: -0.0001

Data Index: 866639 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0207. Min Act: -0.0001

Data Index: 391146 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1253389 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0205. Min Act: -0.0001

Data Index: 697358 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0204. Min Act: -0.0001

Data Index: 587565 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1351667 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0205. Min Act: -0.0001

Data Index: 879677 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1564536 (Python Code)

Max Activating Token Index: 254

Text #13

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1450888 (Python Code)

Max Activating Token Index: 195

Text #14

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1366545 (Python Code)

Max Activating Token Index: 352

Text #15

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1218679 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0195. Min Act: -0.0001

Data Index: 878934 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1466979 (Python Code)

Max Activating Token Index: 423

Text #18

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0194. Min Act: -0.0001

Data Index: 509587 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0196. Min Act: -0.0001

Data Index: 421539 (C4 (Web Text))

Max Activating Token Index: 64