Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1346 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0345. Min Act: -0.0004

Data Index: 1521009 (Python Code)

Max Activating Token Index: 375

Text #1

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1563652 (Python Code)

Max Activating Token Index: 438

Text #2

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0302. Min Act: -0.0004

Data Index: 725768 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1475058 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1328010 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0292. Min Act: -0.0003

Data Index: 662242 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1260593 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1581758 (Python Code)

Max Activating Token Index: 572

Text #8

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0289. Min Act: -0.0004

Data Index: 1131720 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1653394 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0281. Min Act: -0.0003

Data Index: 959934 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1301172 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1619509 (Python Code)

Max Activating Token Index: 571

Text #13

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1416507 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1401011 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0273. Min Act: -0.0003

Data Index: 78721 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1046458 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0281. Min Act: -0.0004

Data Index: 65834 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0274. Min Act: -0.0004

Data Index: 16151 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0279. Min Act: -0.0002

Data Index: 990391 (C4 (Web Text))

Max Activating Token Index: 559