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

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

Neuron 539 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: 0.1853. Min Range: -0.1853

Max Act: 0.1853. Min Act: -0.0001

Data Index: 954942 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1837. Min Act: -0.0000

Data Index: 951539 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1353714 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1774. Min Act: -0.0001

Data Index: 711373 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1682. Min Act: -0.0001

Data Index: 835574 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1705. Min Act: -0.0001

Data Index: 36084 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1768. Min Act: -0.0001

Data Index: 211900 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1640. Min Act: -0.0000

Data Index: 911553 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1710. Min Act: -0.0001

Data Index: 572631 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1519. Min Act: -0.0000

Data Index: 288518 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1619. Min Act: -0.0001

Data Index: 821720 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1571. Min Act: -0.0000

Data Index: 98141 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1047898 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1529. Min Act: -0.0000

Data Index: 986523 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1469. Min Act: -0.0000

Data Index: 710069 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1398. Min Act: -0.0001

Data Index: 73540 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1555. Min Act: -0.0000

Data Index: 972011 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1498. Min Act: -0.0001

Data Index: 708731 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1426. Min Act: -0.0000

Data Index: 150629 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.1853. Min Range: -0.1853

Max Act: 0.1486. Min Act: -0.0000

Data Index: 7681 (C4 (Web Text))

Max Activating Token Index: 914