Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 631 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0003

Data Index: 667871 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0411. Min Act: -0.0002

Data Index: 299167 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0378. Min Act: -0.0003

Data Index: 423345 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0365. Min Act: -0.0002

Data Index: 950506 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0354. Min Act: -0.0002

Data Index: 768478 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1045619 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1319239 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0325. Min Act: -0.0002

Data Index: 65674 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1079470 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0306. Min Act: -0.0002

Data Index: 946696 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0301. Min Act: -0.0002

Data Index: 295642 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1194983 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0279. Min Act: -0.0003

Data Index: 111409 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1087591 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0270. Min Act: -0.0002

Data Index: 862593 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0256. Min Act: -0.0002

Data Index: 762282 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0278. Min Act: -0.0002

Data Index: 412681 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0276. Min Act: -0.0002

Data Index: 532816 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0268. Min Act: -0.0002

Data Index: 28063 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0261. Min Act: -0.0002

Data Index: 868602 (C4 (Web Text))

Max Activating Token Index: 497