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

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

Neuron 27 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: 0.1948. Min Range: -0.1948

Max Act: 0.1840. Min Act: -0.0001

Data Index: 776978 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1948. Min Act: -0.0000

Data Index: 102055 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1844. Min Act: -0.0001

Data Index: 238703 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1161318 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1702. Min Act: -0.0000

Data Index: 721589 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1709. Min Act: -0.0000

Data Index: 247800 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1617. Min Act: -0.0000

Data Index: 117707 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1591. Min Act: -0.0000

Data Index: 441002 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1042150 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1634. Min Act: -0.0000

Data Index: 139273 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1520. Min Act: -0.0000

Data Index: 6775 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1505. Min Act: -0.0000

Data Index: 18836 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1495. Min Act: -0.0000

Data Index: 596862 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1352. Min Act: -0.0001

Data Index: 916038 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1454. Min Act: -0.0000

Data Index: 454505 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1222219 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1417. Min Act: -0.0001

Data Index: 527096 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1158928 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1315. Min Act: -0.0000

Data Index: 237378 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1344. Min Act: -0.0000

Data Index: 249842 (C4 (Web Text))

Max Activating Token Index: 380