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

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

Neuron 47 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1287013 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1751. Min Act: -0.0001

Data Index: 251299 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1589. Min Act: -0.0001

Data Index: 498444 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1692. Min Act: -0.0001

Data Index: 1157917 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1634. Min Act: -0.0001

Data Index: 822594 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1612. Min Act: -0.0000

Data Index: 26468 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1053511 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1549. Min Act: -0.0000

Data Index: 751329 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1553. Min Act: -0.0000

Data Index: 510375 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1539. Min Act: -0.0000

Data Index: 367889 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1537. Min Act: -0.0001

Data Index: 514399 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1612. Min Act: -0.0001

Data Index: 76248 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1610. Min Act: -0.0001

Data Index: 674620 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1545. Min Act: -0.0000

Data Index: 142583 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1428. Min Act: -0.0000

Data Index: 109198 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1051233 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1408. Min Act: -0.0001

Data Index: 410888 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1401. Min Act: -0.0001

Data Index: 388456 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1439. Min Act: -0.0000

Data Index: 312923 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1440. Min Act: -0.0001

Data Index: 931444 (C4 (Web Text))

Max Activating Token Index: 1020