Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 724 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1485802 (Python Code)

Max Activating Token Index: 729

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1537203 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1648023 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1368544 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1615600 (Python Code)

Max Activating Token Index: 859

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1381914 (Python Code)

Max Activating Token Index: 217

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1646773 (Python Code)

Max Activating Token Index: 196

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1642522 (Python Code)

Max Activating Token Index: 278

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1624249 (Python Code)

Max Activating Token Index: 991

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1435144 (Python Code)

Max Activating Token Index: 225

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1446283 (Python Code)

Max Activating Token Index: 811

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0566. Min Act: -0.0001

Data Index: 282613 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1654781 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1462541 (Python Code)

Max Activating Token Index: 899

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1571295 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1394364 (Python Code)

Max Activating Token Index: 264

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1451036 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1530193 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1390168 (Python Code)

Max Activating Token Index: 306

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1375543 (Python Code)

Max Activating Token Index: 403