Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 459 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1505251 (Python Code)

Max Activating Token Index: 410

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1394611 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1568403 (Python Code)

Max Activating Token Index: 885

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1393373 (Python Code)

Max Activating Token Index: 209

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0441. Min Act: -0.0004

Data Index: 357403 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1644814 (Python Code)

Max Activating Token Index: 735

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0414. Min Act: -0.0003

Data Index: 344159 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1565354 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0418. Min Act: -0.0004

Data Index: 230494 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1550662 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1406404 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1383894 (Python Code)

Max Activating Token Index: 868

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1650162 (Python Code)

Max Activating Token Index: 887

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0381. Min Act: -0.0003

Data Index: 215444 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1274411 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1613824 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1328128 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1643109 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1656341 (Python Code)

Max Activating Token Index: 636

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0381. Min Act: -0.0003

Data Index: 487783 (C4 (Web Text))

Max Activating Token Index: 47