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

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

Neuron 63 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: 0.0316. Min Range: -0.0316

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1393903 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1360693 (Python Code)

Max Activating Token Index: 848

Text #2

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1485120 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1387352 (Python Code)

Max Activating Token Index: 669

Text #4

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1464481 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1376431 (Python Code)

Max Activating Token Index: 679

Text #6

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1360589 (Python Code)

Max Activating Token Index: 961

Text #7

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1458427 (Python Code)

Max Activating Token Index: 323

Text #8

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1558815 (Python Code)

Max Activating Token Index: 794

Text #9

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1414424 (Python Code)

Max Activating Token Index: 711

Text #10

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1601526 (Python Code)

Max Activating Token Index: 558

Text #11

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1613207 (Python Code)

Max Activating Token Index: 919

Text #12

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1655995 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1383151 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1651759 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1515122 (Python Code)

Max Activating Token Index: 908

Text #16

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1646962 (Python Code)

Max Activating Token Index: 961

Text #17

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0202. Min Act: -0.0002

Data Index: 343311 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1470925 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1479580 (Python Code)

Max Activating Token Index: 826