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

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

Neuron 1977 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: 0.0343. Min Range: -0.0343

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1507461 (Python Code)

Max Activating Token Index: 394

Text #1

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1465530 (Python Code)

Max Activating Token Index: 806

Text #2

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1369716 (Python Code)

Max Activating Token Index: 941

Text #3

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1377456 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1640367 (Python Code)

Max Activating Token Index: 987

Text #5

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1359896 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1382775 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1610561 (Python Code)

Max Activating Token Index: 568

Text #8

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1552138 (Python Code)

Max Activating Token Index: 428

Text #9

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1452275 (Python Code)

Max Activating Token Index: 534

Text #10

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1373081 (Python Code)

Max Activating Token Index: 525

Text #11

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1441275 (Python Code)

Max Activating Token Index: 1014

Text #12

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1517759 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1360462 (Python Code)

Max Activating Token Index: 576

Text #14

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1575602 (Python Code)

Max Activating Token Index: 800

Text #15

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1424062 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1399434 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1406980 (Python Code)

Max Activating Token Index: 742

Text #18

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1457975 (Python Code)

Max Activating Token Index: 749

Text #19

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1376742 (Python Code)

Max Activating Token Index: 1016