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

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

Neuron 1358 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0429. Min Act: -0.0006

Data Index: 1318791 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0006

Data Index: 607094 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0401. Min Act: -0.0006

Data Index: 1356985 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0401. Min Act: -0.0006

Data Index: 1044929 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0397. Min Act: -0.0006

Data Index: 824305 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0407. Min Act: -0.0006

Data Index: 705930 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0396. Min Act: -0.0006

Data Index: 421289 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0401. Min Act: -0.0006

Data Index: 608275 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0400. Min Act: -0.0006

Data Index: 595260 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0404. Min Act: -0.0006

Data Index: 398399 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0373. Min Act: -0.0006

Data Index: 93739 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0410. Min Act: -0.0006

Data Index: 1437595 (Python Code)

Max Activating Token Index: 372

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0393. Min Act: -0.0006

Data Index: 345054 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1181111 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0381. Min Act: -0.0006

Data Index: 502121 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0389. Min Act: -0.0006

Data Index: 312205 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0387. Min Act: -0.0006

Data Index: 1626537 (Python Code)

Max Activating Token Index: 234

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0377. Min Act: -0.0006

Data Index: 58880 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0378. Min Act: -0.0006

Data Index: 1232850 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0385. Min Act: -0.0006

Data Index: 1215541 (C4 (Web Text))

Max Activating Token Index: 860