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

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

Neuron 5046 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: 1.2493. Min Range: -1.2493

Max Act: 1.2493. Min Act: -0.0000

Data Index: 280300 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 1.2493. Min Range: -1.2493

Max Act: 1.1887. Min Act: -0.0000

Data Index: 804227 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 1.2493. Min Range: -1.2493

Max Act: 1.1072. Min Act: -0.0000

Data Index: 473532 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9471. Min Act: -0.0000

Data Index: 386299 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9367. Min Act: -0.0000

Data Index: 263629 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1326770 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.9498. Min Act: -0.0000

Data Index: 107791 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8910. Min Act: -0.0000

Data Index: 779417 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8052. Min Act: -0.0000

Data Index: 28194 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8432. Min Act: -0.0000

Data Index: 412456 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1235588 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8180. Min Act: -0.0000

Data Index: 603590 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1019021 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7826. Min Act: -0.0000

Data Index: 53038 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1061535 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6795. Min Act: -0.0000

Data Index: 438666 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7034. Min Act: -0.0000

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1105694 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7063. Min Act: -0.0000

Data Index: 40437 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1051646 (C4 (Web Text))

Max Activating Token Index: 606