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

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

Neuron 383 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: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1383588 (Python Code)

Max Activating Token Index: 736

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1648689 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1641349 (Python Code)

Max Activating Token Index: 301

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1486682 (Python Code)

Max Activating Token Index: 671

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1454704 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1613546 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0369. Min Act: -0.0002

Data Index: 89041 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0362. Min Act: -0.0002

Data Index: 251134 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0358. Min Act: -0.0002

Data Index: 746471 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0357. Min Act: -0.0002

Data Index: 202403 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0359. Min Act: -0.0002

Data Index: 377024 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0358. Min Act: -0.0002

Data Index: 865256 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0356. Min Act: -0.0002

Data Index: 569191 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0360. Min Act: -0.0002

Data Index: 833551 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1478318 (Python Code)

Max Activating Token Index: 87

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0349. Min Act: -0.0002

Data Index: 786616 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0351. Min Act: -0.0002

Data Index: 495235 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0344. Min Act: -0.0002

Data Index: 440703 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1216995 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0354. Min Act: -0.0002

Data Index: 867520 (C4 (Web Text))

Max Activating Token Index: 425