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

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

Neuron 1773 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: 0.2016. Min Range: -0.2016

Max Act: 0.1855. Min Act: -0.0000

Data Index: 750630 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.2016. Min Act: -0.0001

Data Index: 592795 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1765. Min Act: -0.0000

Data Index: 266649 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1758. Min Act: -0.0001

Data Index: 728243 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1717. Min Act: -0.0001

Data Index: 222489 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1177732 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1594. Min Act: -0.0001

Data Index: 796377 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1649. Min Act: -0.0000

Data Index: 235855 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1058374 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1703. Min Act: -0.0000

Data Index: 394693 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1689. Min Act: -0.0000

Data Index: 568993 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1577. Min Act: -0.0000

Data Index: 784697 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1221733 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1640. Min Act: -0.0001

Data Index: 577640 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1579. Min Act: -0.0000

Data Index: 523592 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1554. Min Act: -0.0000

Data Index: 578320 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1537. Min Act: -0.0000

Data Index: 41753 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1060024 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1631. Min Act: -0.0001

Data Index: 802668 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.2016. Min Range: -0.2016

Max Act: 0.1535. Min Act: -0.0001

Data Index: 888744 (C4 (Web Text))

Max Activating Token Index: 506