Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 888 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: -0.0006

Data Index: 1498543 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1607533 (Python Code)

Max Activating Token Index: 620

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1488809 (Python Code)

Max Activating Token Index: 250

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1429544 (Python Code)

Max Activating Token Index: 569

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1413509 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1469896 (Python Code)

Max Activating Token Index: 428

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1626884 (Python Code)

Max Activating Token Index: 454

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1614975 (Python Code)

Max Activating Token Index: 964

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1520590 (Python Code)

Max Activating Token Index: 919

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1391739 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1401607 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1424516 (Python Code)

Max Activating Token Index: 959

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1385724 (Python Code)

Max Activating Token Index: 533

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1635707 (Python Code)

Max Activating Token Index: 924

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1584043 (Python Code)

Max Activating Token Index: 489

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1609952 (Python Code)

Max Activating Token Index: 480

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0245. Min Act: -0.0005

Data Index: 1511472 (Python Code)

Max Activating Token Index: 933

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1361542 (Python Code)

Max Activating Token Index: 632

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1373350 (Python Code)

Max Activating Token Index: 602

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1425535 (Python Code)

Max Activating Token Index: 604