Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 782 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0002

Data Index: 25943 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0729. Min Act: -0.0002

Data Index: 618407 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0688. Min Act: -0.0002

Data Index: 971477 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0673. Min Act: -0.0002

Data Index: 131033 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0691. Min Act: -0.0000

Data Index: 695092 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0644. Min Act: -0.0002

Data Index: 257734 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0650. Min Act: -0.0000

Data Index: 546234 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0633. Min Act: -0.0002

Data Index: 97263 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0619. Min Act: -0.0002

Data Index: 407979 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1006556 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0596. Min Act: -0.0002

Data Index: 573756 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0601. Min Act: -0.0001

Data Index: 893720 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0591. Min Act: -0.0002

Data Index: 276598 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0582. Min Act: -0.0001

Data Index: 240979 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1044819 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1164731 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1334991 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0578. Min Act: -0.0002

Data Index: 786950 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1351157 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0570. Min Act: -0.0000

Data Index: 930710 (C4 (Web Text))

Max Activating Token Index: 163