Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2617 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1551073 (Python Code)

Max Activating Token Index: 152

Text #1

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1597030 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1779. Min Act: 0.0001

Data Index: 1478359 (Python Code)

Max Activating Token Index: 597

Text #3

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1400758 (Python Code)

Max Activating Token Index: 551

Text #4

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1598. Min Act: 0.0001

Data Index: 1500341 (Python Code)

Max Activating Token Index: 368

Text #5

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1632. Min Act: 0.0001

Data Index: 1474514 (Python Code)

Max Activating Token Index: 398

Text #6

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1644897 (Python Code)

Max Activating Token Index: 174

Text #7

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1504845 (Python Code)

Max Activating Token Index: 905

Text #8

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1327640 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1543436 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1593. Min Act: -0.0000

Data Index: 678079 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1456356 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1541. Min Act: -0.0000

Data Index: 74859 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1494. Min Act: 0.0000

Data Index: 1436394 (Python Code)

Max Activating Token Index: 484

Text #14

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1070553 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1493. Min Act: -0.0000

Data Index: 794140 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1472. Min Act: 0.0000

Data Index: 1566066 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1477. Min Act: -0.0000

Data Index: 624694 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1479732 (Python Code)

Max Activating Token Index: 706

Text #19

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1381263 (Python Code)

Max Activating Token Index: 287