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

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

Neuron 755 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1383735 (Python Code)

Max Activating Token Index: 832

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1379831 (Python Code)

Max Activating Token Index: 547

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1642833 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1625262 (Python Code)

Max Activating Token Index: 863

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1608555 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1576975 (Python Code)

Max Activating Token Index: 949

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1624954 (Python Code)

Max Activating Token Index: 250

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1560194 (Python Code)

Max Activating Token Index: 288

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1641503 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1628794 (Python Code)

Max Activating Token Index: 300

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1505546 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0376. Min Act: -0.0003

Data Index: 755361 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1633755 (Python Code)

Max Activating Token Index: 1010

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1441564 (Python Code)

Max Activating Token Index: 67

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1410422 (Python Code)

Max Activating Token Index: 362

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1602852 (Python Code)

Max Activating Token Index: 846

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1392822 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1567001 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0352. Min Act: -0.0004

Data Index: 1611125 (Python Code)

Max Activating Token Index: 352

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0350. Min Act: -0.0003

Data Index: 1604132 (Python Code)

Max Activating Token Index: 883