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

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

Neuron 5964 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: 2.5397. Min Range: -2.5397

Max Act: 2.5397. Min Act: -0.0000

Data Index: 390110 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 2.5397. Min Range: -2.5397

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1158017 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 2.5397. Min Range: -2.5397

Max Act: 2.2679. Min Act: -0.0000

Data Index: 99443 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 2.5397. Min Range: -2.5397

Max Act: 2.2456. Min Act: -0.0000

Data Index: 764344 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 2.5397. Min Range: -2.5397

Max Act: 2.3572. Min Act: -0.0000

Data Index: 901506 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 2.5397. Min Range: -2.5397

Max Act: 2.1979. Min Act: -0.0000

Data Index: 561612 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.8712. Min Act: -0.0000

Data Index: 540600 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 2.5397. Min Range: -2.5397

Max Act: 2.0723. Min Act: -0.0000

Data Index: 1279450 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 2.5397. Min Range: -2.5397

Max Act: 2.0666. Min Act: -0.0000

Data Index: 1007613 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.9959. Min Act: -0.0000

Data Index: 229879 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.5397. Min Range: -2.5397

Max Act: 2.1024. Min Act: -0.0000

Data Index: 1349547 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.9898. Min Act: -0.0000

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.8686. Min Act: -0.0000

Data Index: 403809 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.8514. Min Act: -0.0000

Data Index: 224230 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.7259. Min Act: -0.0000

Data Index: 685688 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.8953. Min Act: -0.0000

Data Index: 1505167 (Python Code)

Max Activating Token Index: 712

Text #16

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.9109. Min Act: -0.0000

Data Index: 1436697 (Python Code)

Max Activating Token Index: 533

Text #17

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.9081. Min Act: -0.0000

Data Index: 1543003 (Python Code)

Max Activating Token Index: 609

Text #18

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.9877. Min Act: -0.0000

Data Index: 87230 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 2.5397. Min Range: -2.5397

Max Act: 1.6364. Min Act: -0.0000

Data Index: 829715 (C4 (Web Text))

Max Activating Token Index: 829