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

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

Neuron 4005 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.7698. Min Act: -0.0000

Data Index: 868403 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6954. Min Act: -0.0000

Data Index: 111105 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.7008. Min Act: -0.0000

Data Index: 944522 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.7019. Min Act: -0.0000

Data Index: 631677 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1302231 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6968. Min Act: -0.0000

Data Index: 83567 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.7413. Min Act: -0.0000

Data Index: 487146 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1626409 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6851. Min Act: -0.0000

Data Index: 787896 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6503. Min Act: -0.0000

Data Index: 496151 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6703. Min Act: -0.0000

Data Index: 339006 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6633. Min Act: -0.0000

Data Index: 735879 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1182071 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1212794 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1054551 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6495. Min Act: -0.0000

Data Index: 878552 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1384761 (Python Code)

Max Activating Token Index: 671

Text #17

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6329. Min Act: -0.0000

Data Index: 126170 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6345. Min Act: -0.0000

Data Index: 339712 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.7698. Min Range: -0.7698

Max Act: 0.6093. Min Act: -0.0000

Data Index: 944571 (C4 (Web Text))

Max Activating Token Index: 1001