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

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

Neuron 2332 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: 0.9159. Min Range: -0.9159

Max Act: 0.9038. Min Act: -0.0002

Data Index: 1431962 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.9159. Min Act: -0.0002

Data Index: 1491856 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8836. Min Act: -0.0002

Data Index: 1614517 (Python Code)

Max Activating Token Index: 547

Text #3

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8847. Min Act: -0.0002

Data Index: 1457193 (Python Code)

Max Activating Token Index: 320

Text #4

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8628. Min Act: -0.0002

Data Index: 1490223 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8600. Min Act: -0.0002

Data Index: 1430019 (Python Code)

Max Activating Token Index: 391

Text #6

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8544. Min Act: -0.0002

Data Index: 1495927 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8650. Min Act: -0.0002

Data Index: 1380926 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8727. Min Act: -0.0002

Data Index: 1632347 (Python Code)

Max Activating Token Index: 689

Text #9

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8490. Min Act: -0.0002

Data Index: 1375929 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8428. Min Act: -0.0002

Data Index: 1471388 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8483. Min Act: -0.0002

Data Index: 1574944 (Python Code)

Max Activating Token Index: 86

Text #12

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8270. Min Act: -0.0002

Data Index: 1462262 (Python Code)

Max Activating Token Index: 330

Text #13

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8178. Min Act: -0.0002

Data Index: 1533410 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8397. Min Act: -0.0002

Data Index: 1376473 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8420. Min Act: -0.0002

Data Index: 1402330 (Python Code)

Max Activating Token Index: 338

Text #16

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8284. Min Act: -0.0002

Data Index: 1558920 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8243. Min Act: -0.0002

Data Index: 1499014 (Python Code)

Max Activating Token Index: 408

Text #18

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8323. Min Act: -0.0002

Data Index: 1399487 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8313. Min Act: -0.0002

Data Index: 1415998 (Python Code)

Max Activating Token Index: 175