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

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

Neuron 637 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0554. Min Act: -0.0001

Data Index: 535826 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0477. Min Act: -0.0001

Data Index: 348787 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1380965 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1123218 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1379366 (Python Code)

Max Activating Token Index: 204

Text #5

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0467. Min Act: -0.0001

Data Index: 823489 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1525606 (Python Code)

Max Activating Token Index: 493

Text #7

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0421. Min Act: -0.0001

Data Index: 77303 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0419. Min Act: -0.0001

Data Index: 638345 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1327996 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0409. Min Act: -0.0001

Data Index: 41047 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0398. Min Act: -0.0001

Data Index: 1557639 (Python Code)

Max Activating Token Index: 628

Text #12

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0434. Min Act: -0.0001

Data Index: 358619 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0416. Min Act: -0.0001

Data Index: 119979 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0379. Min Act: -0.0001

Data Index: 283575 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1634803 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0391. Min Act: -0.0001

Data Index: 212644 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0347. Min Act: -0.0001

Data Index: 309106 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0394. Min Act: -0.0001

Data Index: 251744 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1223469 (C4 (Web Text))

Max Activating Token Index: 180