Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3654 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1354924 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1075387 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0637. Min Act: -0.0001

Data Index: 875399 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0604. Min Act: -0.0001

Data Index: 589567 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0585. Min Act: -0.0001

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0528. Min Act: -0.0001

Data Index: 227118 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1042992 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0463. Min Act: -0.0000

Data Index: 876799 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0458. Min Act: -0.0001

Data Index: 39542 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0424. Min Act: -0.0001

Data Index: 603744 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0423. Min Act: -0.0001

Data Index: 887309 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0396. Min Act: -0.0000

Data Index: 115148 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0390. Min Act: -0.0000

Data Index: 191430 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0367. Min Act: -0.0001

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1169983 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0373. Min Act: -0.0000

Data Index: 344036 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0368. Min Act: -0.0000

Data Index: 93632 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1178550 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1233880 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1240732 (C4 (Web Text))

Max Activating Token Index: 582