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

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

Neuron 981 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0006

Data Index: 226808 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0387. Min Act: -0.0005

Data Index: 239401 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0409. Min Act: -0.0005

Data Index: 966775 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0392. Min Act: -0.0006

Data Index: 284912 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0365. Min Act: -0.0006

Data Index: 586025 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0387. Min Act: -0.0006

Data Index: 804775 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0393. Min Act: -0.0005

Data Index: 684299 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0373. Min Act: -0.0006

Data Index: 80602 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0385. Min Act: -0.0006

Data Index: 1265542 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0376. Min Act: -0.0006

Data Index: 755775 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0382. Min Act: -0.0006

Data Index: 255846 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0390. Min Act: -0.0006

Data Index: 358814 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1459135 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1648219 (Python Code)

Max Activating Token Index: 214

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0371. Min Act: -0.0005

Data Index: 1209407 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0386. Min Act: -0.0005

Data Index: 32448 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0372. Min Act: -0.0006

Data Index: 475483 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1354147 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0361. Min Act: -0.0006

Data Index: 761303 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0356. Min Act: -0.0006

Data Index: 492758 (C4 (Web Text))

Max Activating Token Index: 633