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

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

Neuron 1758 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1531162 (Python Code)

Max Activating Token Index: 807

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1599361 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1482238 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1554296 (Python Code)

Max Activating Token Index: 955

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1398483 (Python Code)

Max Activating Token Index: 650

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1512468 (Python Code)

Max Activating Token Index: 609

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1582134 (Python Code)

Max Activating Token Index: 994

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1649293 (Python Code)

Max Activating Token Index: 267

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1449903 (Python Code)

Max Activating Token Index: 277

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1441683 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0588. Min Act: 0.0000

Data Index: 1411844 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1522850 (Python Code)

Max Activating Token Index: 289

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1365922 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0529. Min Act: 0.0001

Data Index: 1456915 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1418633 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1562219 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1494170 (Python Code)

Max Activating Token Index: 780

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1471492 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1627481 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1611806 (Python Code)

Max Activating Token Index: 996