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

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

Neuron 5202 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.7622. Min Act: -0.0000

Data Index: 482959 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.3664. Min Act: -0.0000

Data Index: 855873 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.3915. Min Act: -0.0000

Data Index: 729379 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.3867. Min Act: -0.0000

Data Index: 188667 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.3006. Min Act: -0.0000

Data Index: 603048 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.1728. Min Act: -0.0000

Data Index: 1155732 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1329351 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.1689. Min Act: -0.0000

Data Index: 919247 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1315357 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.1159. Min Act: -0.0000

Data Index: 219189 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.1058. Min Act: -0.0000

Data Index: 110884 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1024805 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1175309 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.0833. Min Act: -0.0000

Data Index: 655944 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.0124. Min Act: -0.0000

Data Index: 822616 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.7622. Min Range: -1.7622

Max Act: 0.9930. Min Act: -0.0000

Data Index: 600982 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.0430. Min Act: -0.0000

Data Index: 896203 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.1428. Min Act: -0.0000

Data Index: 142298 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.0514. Min Act: -0.0000

Data Index: 171384 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 1.7622. Min Range: -1.7622

Max Act: 1.0480. Min Act: -0.0000

Data Index: 18239 (C4 (Web Text))

Max Activating Token Index: 225