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

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

Neuron 3353 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1169002 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0632. Min Act: -0.0003

Data Index: 1401462 (Python Code)

Max Activating Token Index: 669

Text #2

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1544632 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1498447 (Python Code)

Max Activating Token Index: 895

Text #4

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1633074 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1099387 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1552740 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1393309 (Python Code)

Max Activating Token Index: 418

Text #8

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0600. Min Act: -0.0003

Data Index: 828475 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0584. Min Act: -0.0003

Data Index: 811164 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1310411 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1426283 (Python Code)

Max Activating Token Index: 570

Text #12

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1576219 (Python Code)

Max Activating Token Index: 834

Text #13

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1597868 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1363394 (Python Code)

Max Activating Token Index: 97

Text #15

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1640080 (Python Code)

Max Activating Token Index: 285

Text #16

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1432130 (Python Code)

Max Activating Token Index: 646

Text #17

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1471398 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1381000 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1495942 (Python Code)

Max Activating Token Index: 35