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

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

Neuron 222 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1501509 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1618855 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1575925 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0644. Min Act: -0.0002

Data Index: 348475 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1590308 (Python Code)

Max Activating Token Index: 496

Text #5

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0599. Min Act: -0.0001

Data Index: 518327 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0612. Min Act: -0.0002

Data Index: 877668 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0590. Min Act: -0.0002

Data Index: 335594 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1106972 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1471145 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0621. Min Act: -0.0001

Data Index: 318895 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0613. Min Act: -0.0002

Data Index: 546704 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1446557 (Python Code)

Max Activating Token Index: 120

Text #13

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0572. Min Act: -0.0001

Data Index: 656551 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1451491 (Python Code)

Max Activating Token Index: 549

Text #15

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1178059 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1248971 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0555. Min Act: -0.0001

Data Index: 1607483 (Python Code)

Max Activating Token Index: 93

Text #18

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0557. Min Act: -0.0001

Data Index: 277645 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0595. Min Act: -0.0002

Data Index: 86105 (C4 (Web Text))

Max Activating Token Index: 693