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

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

Neuron 639 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: 0.2180. Min Range: -0.2180

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1236379 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1250492 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1740. Min Act: -0.0000

Data Index: 984073 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1713. Min Act: -0.0000

Data Index: 104701 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1781. Min Act: -0.0000

Data Index: 60802 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1715. Min Act: -0.0000

Data Index: 989990 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1699. Min Act: -0.0000

Data Index: 303356 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1753. Min Act: -0.0000

Data Index: 100023 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1344481 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1631. Min Act: -0.0000

Data Index: 599293 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1266673 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1537720 (Python Code)

Max Activating Token Index: 708

Text #12

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1616. Min Act: -0.0000

Data Index: 562130 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1446. Min Act: -0.0000

Data Index: 523960 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1653. Min Act: -0.0000

Data Index: 386558 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1672. Min Act: -0.0000

Data Index: 192375 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1577. Min Act: -0.0000

Data Index: 386723 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1460. Min Act: -0.0001

Data Index: 530777 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1182581 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1021522 (C4 (Web Text))

Max Activating Token Index: 61