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

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

Neuron 3168 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1136100 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1142688 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1886. Min Act: -0.0001

Data Index: 56727 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1828. Min Act: -0.0001

Data Index: 297968 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1821. Min Act: -0.0000

Data Index: 316119 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1795. Min Act: -0.0001

Data Index: 756621 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1749. Min Act: -0.0001

Data Index: 272997 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1051132 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1269138 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1693. Min Act: -0.0001

Data Index: 116050 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1729. Min Act: -0.0001

Data Index: 476509 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1031369 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1239328 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1283789 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1269584 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1499. Min Act: -0.0001

Data Index: 145495 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1501. Min Act: -0.0001

Data Index: 15866 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1581. Min Act: -0.0001

Data Index: 453140 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1330764 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1530. Min Act: -0.0001

Data Index: 557023 (C4 (Web Text))

Max Activating Token Index: 237