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

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

Neuron 103 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: 0.0435. Min Range: -0.0435

Max Act: 0.0415. Min Act: -0.0006

Data Index: 1483276 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0412. Min Act: -0.0006

Data Index: 1532293 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1432806 (Python Code)

Max Activating Token Index: 735

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1478770 (Python Code)

Max Activating Token Index: 995

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1463306 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1010585 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0396. Min Act: -0.0006

Data Index: 26786 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0395. Min Act: -0.0006

Data Index: 562198 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0379. Min Act: -0.0006

Data Index: 251751 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1409233 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0350. Min Act: -0.0006

Data Index: 1372107 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1453864 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1620483 (Python Code)

Max Activating Token Index: 380

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1488084 (Python Code)

Max Activating Token Index: 416

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0377. Min Act: -0.0006

Data Index: 503329 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1515179 (Python Code)

Max Activating Token Index: 298

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0376. Min Act: -0.0006

Data Index: 611922 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0348. Min Act: -0.0005

Data Index: 1372663 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1444687 (Python Code)

Max Activating Token Index: 785

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0368. Min Act: -0.0006

Data Index: 347710 (C4 (Web Text))

Max Activating Token Index: 709