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

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

Neuron 1411 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0005

Data Index: 1521155 (Python Code)

Max Activating Token Index: 422

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0443. Min Act: -0.0005

Data Index: 1636368 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0441. Min Act: -0.0005

Data Index: 1435509 (Python Code)

Max Activating Token Index: 203

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0423. Min Act: -0.0005

Data Index: 1538445 (Python Code)

Max Activating Token Index: 349

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0421. Min Act: -0.0005

Data Index: 1582567 (Python Code)

Max Activating Token Index: 137

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0413. Min Act: -0.0005

Data Index: 1547734 (Python Code)

Max Activating Token Index: 951

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0410. Min Act: -0.0005

Data Index: 1426395 (Python Code)

Max Activating Token Index: 399

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0407. Min Act: -0.0005

Data Index: 1506529 (Python Code)

Max Activating Token Index: 595

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0424. Min Act: -0.0005

Data Index: 1579710 (Python Code)

Max Activating Token Index: 554

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0414. Min Act: -0.0005

Data Index: 1416946 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0405. Min Act: -0.0005

Data Index: 1456130 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0420. Min Act: -0.0005

Data Index: 1415373 (Python Code)

Max Activating Token Index: 626

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0408. Min Act: -0.0005

Data Index: 1419958 (Python Code)

Max Activating Token Index: 97

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0412. Min Act: -0.0005

Data Index: 1438241 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0394. Min Act: -0.0005

Data Index: 1456837 (Python Code)

Max Activating Token Index: 560

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0404. Min Act: -0.0005

Data Index: 1593492 (Python Code)

Max Activating Token Index: 192

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0419. Min Act: -0.0005

Data Index: 1454944 (Python Code)

Max Activating Token Index: 84

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0409. Min Act: -0.0005

Data Index: 1595450 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0400. Min Act: -0.0005

Data Index: 1461767 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0398. Min Act: -0.0005

Data Index: 1566524 (Python Code)

Max Activating Token Index: 959