Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 964 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0756. Min Act: -0.0000

Data Index: 488086 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0750. Min Act: -0.0000

Data Index: 33636 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0691. Min Act: -0.0000

Data Index: 38657 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0665. Min Act: -0.0000

Data Index: 181345 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0634. Min Act: -0.0000

Data Index: 94658 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0638. Min Act: -0.0000

Data Index: 121220 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0610. Min Act: -0.0000

Data Index: 235789 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0575. Min Act: -0.0000

Data Index: 682805 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0596. Min Act: -0.0000

Data Index: 249902 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1018865 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0563. Min Act: -0.0000

Data Index: 193130 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0540. Min Act: -0.0000

Data Index: 844060 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0541. Min Act: -0.0000

Data Index: 169384 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0570. Min Act: -0.0000

Data Index: 358009 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0561. Min Act: -0.0001

Data Index: 320692 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0559. Min Act: -0.0000

Data Index: 819695 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0571. Min Act: -0.0000

Data Index: 958801 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1193563 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1335599 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0523. Min Act: -0.0000

Data Index: 393332 (C4 (Web Text))

Max Activating Token Index: 291