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

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

Neuron 1632 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1244713 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0662. Min Act: -0.0001

Data Index: 432472 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0654. Min Act: -0.0001

Data Index: 815441 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1121137 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1028393 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1085842 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0613. Min Act: -0.0001

Data Index: 748858 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0582. Min Act: -0.0001

Data Index: 223787 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0561. Min Act: -0.0001

Data Index: 907884 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1157425 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0578. Min Act: -0.0001

Data Index: 102514 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0614. Min Act: -0.0001

Data Index: 233643 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0548. Min Act: -0.0001

Data Index: 779989 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0520. Min Act: -0.0001

Data Index: 444203 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0571. Min Act: -0.0001

Data Index: 581380 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0545. Min Act: -0.0001

Data Index: 68244 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1052786 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0589. Min Act: -0.0001

Data Index: 85786 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1081090 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0548. Min Act: -0.0001

Data Index: 495416 (C4 (Web Text))

Max Activating Token Index: 913