Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3863 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1004163 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0453. Min Act: -0.0000

Data Index: 616402 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0463. Min Act: -0.0000

Data Index: 248953 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0385. Min Act: -0.0000

Data Index: 110331 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1030935 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0420. Min Act: -0.0000

Data Index: 721626 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0412. Min Act: -0.0000

Data Index: 244162 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0393. Min Act: -0.0000

Data Index: 241590 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0408. Min Act: -0.0000

Data Index: 955619 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0403. Min Act: -0.0000

Data Index: 632197 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0367. Min Act: -0.0000

Data Index: 981976 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1460907 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0390. Min Act: -0.0000

Data Index: 927797 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0389. Min Act: -0.0000

Data Index: 953099 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0373. Min Act: -0.0000

Data Index: 117339 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1616942 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0373. Min Act: -0.0000

Data Index: 771689 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0355. Min Act: -0.0000

Data Index: 677780 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0353. Min Act: -0.0000

Data Index: 641822 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0397. Min Act: -0.0000

Data Index: 25153 (C4 (Web Text))

Max Activating Token Index: 25