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

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

Neuron 2016 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: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1339499 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0717. Min Act: -0.0000

Data Index: 544976 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0671. Min Act: -0.0000

Data Index: 141677 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1202142 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0553. Min Act: -0.0000

Data Index: 736852 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0648. Min Act: -0.0000

Data Index: 321772 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0552. Min Act: -0.0000

Data Index: 301091 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0591. Min Act: -0.0000

Data Index: 189948 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1081092 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0556. Min Act: -0.0000

Data Index: 764794 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0544. Min Act: -0.0000

Data Index: 747645 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0516. Min Act: -0.0000

Data Index: 244718 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0542. Min Act: -0.0000

Data Index: 466742 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1251109 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1148754 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0538. Min Act: -0.0000

Data Index: 990802 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0536. Min Act: -0.0000

Data Index: 37326 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0555. Min Act: -0.0000

Data Index: 554693 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0509. Min Act: -0.0001

Data Index: 192984 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0521. Min Act: -0.0000

Data Index: 545256 (C4 (Web Text))

Max Activating Token Index: 208