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

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

Neuron 1966 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: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0003

Data Index: 827487 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0469. Min Act: -0.0002

Data Index: 3410 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1534617 (Python Code)

Max Activating Token Index: 94

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0436. Min Act: -0.0003

Data Index: 814490 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1469565 (Python Code)

Max Activating Token Index: 1009

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0443. Min Act: -0.0002

Data Index: 17605 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0447. Min Act: -0.0003

Data Index: 861948 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0408. Min Act: -0.0002

Data Index: 873153 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0449. Min Act: -0.0003

Data Index: 128706 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1113071 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0394. Min Act: -0.0002

Data Index: 36984 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1459741 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1122256 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0386. Min Act: -0.0004

Data Index: 453980 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0393. Min Act: -0.0003

Data Index: 936751 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1574814 (Python Code)

Max Activating Token Index: 831

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0392. Min Act: -0.0002

Data Index: 639991 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0382. Min Act: -0.0003

Data Index: 842298 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1518610 (Python Code)

Max Activating Token Index: 742

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0378. Min Act: -0.0003

Data Index: 134641 (C4 (Web Text))

Max Activating Token Index: 63