Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2723 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1279830 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0833. Min Act: -0.0001

Data Index: 37172 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0799. Min Act: -0.0001

Data Index: 590086 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0741. Min Act: 0.0000

Data Index: 528038 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0744. Min Act: -0.0001

Data Index: 505822 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0702. Min Act: -0.0001

Data Index: 903596 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1216641 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0652. Min Act: -0.0001

Data Index: 519280 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1124834 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0655. Min Act: -0.0001

Data Index: 641607 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0601. Min Act: -0.0001

Data Index: 828758 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0610. Min Act: -0.0001

Data Index: 335858 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1241674 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0563. Min Act: -0.0001

Data Index: 448448 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1186086 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0597. Min Act: -0.0001

Data Index: 546306 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0614. Min Act: -0.0001

Data Index: 218838 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1064572 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1192381 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0562. Min Act: -0.0001

Data Index: 133303 (C4 (Web Text))

Max Activating Token Index: 371