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

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

Neuron 1587 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1129992 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.7979. Min Act: -0.0001

Data Index: 1095713 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.7178. Min Act: -0.0001

Data Index: 455666 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.8423. Min Act: -0.0001

Data Index: 1328190 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6630. Min Act: -0.0001

Data Index: 691930 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6759. Min Act: -0.0001

Data Index: 18586 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6609. Min Act: -0.0001

Data Index: 1592332 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6629. Min Act: -0.0001

Data Index: 1341565 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.7379. Min Act: -0.0001

Data Index: 132806 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6561. Min Act: -0.0001

Data Index: 874882 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5498. Min Act: -0.0001

Data Index: 447186 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5759. Min Act: -0.0001

Data Index: 836746 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5517. Min Act: -0.0001

Data Index: 819498 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5704. Min Act: -0.0001

Data Index: 1157803 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5505. Min Act: -0.0001

Data Index: 143410 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5847. Min Act: -0.0001

Data Index: 584019 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5867. Min Act: -0.0001

Data Index: 77224 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5667. Min Act: -0.0001

Data Index: 704253 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5564. Min Act: -0.0001

Data Index: 1193474 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5866. Min Act: -0.0001

Data Index: 1348544 (C4 (Web Text))

Max Activating Token Index: 749