Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1366 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1293996 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0618. Min Act: -0.0001

Data Index: 994812 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0646. Min Act: -0.0001

Data Index: 898512 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1473011 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0571. Min Act: -0.0001

Data Index: 390526 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1607953 (Python Code)

Max Activating Token Index: 182

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1537480 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1108673 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0593. Min Act: -0.0001

Data Index: 228073 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0624. Min Act: -0.0001

Data Index: 83114 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0552. Min Act: -0.0001

Data Index: 741712 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0538. Min Act: -0.0001

Data Index: 765611 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1277597 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0515. Min Act: -0.0001

Data Index: 384992 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0530. Min Act: -0.0001

Data Index: 474683 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1419556 (Python Code)

Max Activating Token Index: 751

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0541. Min Act: -0.0001

Data Index: 65648 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0524. Min Act: -0.0001

Data Index: 783081 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0522. Min Act: -0.0001

Data Index: 987232 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1606931 (Python Code)

Max Activating Token Index: 830