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

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

Neuron 1212 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1035270 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0000

Data Index: 682146 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1599726 (Python Code)

Max Activating Token Index: 567

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0631. Min Act: -0.0000

Data Index: 286429 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0588. Min Act: -0.0000

Data Index: 696259 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0614. Min Act: -0.0000

Data Index: 987354 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1377172 (Python Code)

Max Activating Token Index: 677

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0641. Min Act: -0.0000

Data Index: 564043 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0569. Min Act: -0.0000

Data Index: 693128 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1477875 (Python Code)

Max Activating Token Index: 582

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1159001 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0558. Min Act: -0.0000

Data Index: 232111 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1653522 (Python Code)

Max Activating Token Index: 276

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0559. Min Act: -0.0000

Data Index: 699553 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1427643 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0523. Min Act: -0.0000

Data Index: 731154 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0519. Min Act: -0.0000

Data Index: 192572 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1055086 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0536. Min Act: -0.0000

Data Index: 722067 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0552. Min Act: -0.0000

Data Index: 305478 (C4 (Web Text))

Max Activating Token Index: 729