Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1050 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0006

Data Index: 1231798 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0414. Min Act: -0.0006

Data Index: 741747 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0417. Min Act: -0.0006

Data Index: 990709 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0400. Min Act: -0.0006

Data Index: 427281 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0403. Min Act: -0.0006

Data Index: 908934 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0409. Min Act: -0.0006

Data Index: 801505 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0358. Min Act: -0.0006

Data Index: 42810 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0410. Min Act: -0.0006

Data Index: 489779 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0392. Min Act: -0.0006

Data Index: 868055 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1284462 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0394. Min Act: -0.0006

Data Index: 684429 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0394. Min Act: -0.0006

Data Index: 967394 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0377. Min Act: -0.0006

Data Index: 193758 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0401. Min Act: -0.0006

Data Index: 639541 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0384. Min Act: -0.0006

Data Index: 1324772 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0359. Min Act: -0.0006

Data Index: 226732 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1287862 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0349. Min Act: -0.0006

Data Index: 1149823 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0382. Min Act: -0.0006

Data Index: 992485 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0383. Min Act: -0.0006

Data Index: 850774 (C4 (Web Text))

Max Activating Token Index: 702