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

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

Neuron 1272 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: 0.0498. Min Range: -0.0498

Max Act: 0.0498. Min Act: -0.0005

Data Index: 225620 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0453. Min Act: -0.0005

Data Index: 1077922 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0438. Min Act: -0.0005

Data Index: 1349120 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1336475 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0388. Min Act: -0.0005

Data Index: 150826 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0401. Min Act: -0.0005

Data Index: 27002 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0387. Min Act: -0.0005

Data Index: 129287 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0392. Min Act: -0.0005

Data Index: 31421 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0428. Min Act: -0.0005

Data Index: 220265 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0375. Min Act: -0.0005

Data Index: 709055 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0383. Min Act: -0.0005

Data Index: 371893 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0396. Min Act: -0.0005

Data Index: 510137 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0425. Min Act: -0.0005

Data Index: 1214135 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0410. Min Act: -0.0005

Data Index: 984246 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0376. Min Act: -0.0005

Data Index: 1576143 (Python Code)

Max Activating Token Index: 961

Text #15

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0431. Min Act: -0.0005

Data Index: 588688 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0431. Min Act: -0.0005

Data Index: 826417 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0393. Min Act: -0.0005

Data Index: 794833 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0415. Min Act: -0.0005

Data Index: 1357712 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0437. Min Act: -0.0005

Data Index: 990489 (C4 (Web Text))

Max Activating Token Index: 648