Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 894 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3640. Min Range: -2.3640

Max Act: 2.2744. Min Act: -0.0000

Data Index: 615001 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 2.3640. Min Range: -2.3640

Max Act: 2.2536. Min Act: -0.0000

Data Index: 1212840 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 2.3640. Min Range: -2.3640

Max Act: 2.3640. Min Act: -0.0000

Data Index: 1352502 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 2.3640. Min Range: -2.3640

Max Act: 2.2000. Min Act: -0.0000

Data Index: 1178547 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 2.3640. Min Range: -2.3640

Max Act: 2.0681. Min Act: -0.0000

Data Index: 550907 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.9985. Min Act: -0.0000

Data Index: 461023 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.9731. Min Act: -0.0000

Data Index: 1328189 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.9725. Min Act: -0.0000

Data Index: 241957 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 2.3640. Min Range: -2.3640

Max Act: 2.0594. Min Act: -0.0000

Data Index: 1062506 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.7915. Min Act: -0.0000

Data Index: 62267 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.9453. Min Act: -0.0000

Data Index: 871940 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.7816. Min Act: -0.0000

Data Index: 1204968 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.7054. Min Act: -0.0000

Data Index: 180754 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1002563 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.6480. Min Act: -0.0000

Data Index: 1068631 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.6325. Min Act: -0.0000

Data Index: 860973 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.6126. Min Act: -0.0000

Data Index: 350731 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1175342 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.5809. Min Act: -0.0000

Data Index: 1172669 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 2.3640. Min Range: -2.3640

Max Act: 1.6664. Min Act: -0.0000

Data Index: 114302 (C4 (Web Text))

Max Activating Token Index: 637