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

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

Neuron 3299 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.4540. Min Act: -0.0000

Data Index: 359727 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3935. Min Act: -0.0000

Data Index: 764803 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3781. Min Act: -0.0000

Data Index: 3258 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1357326 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1301078 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3706. Min Act: -0.0000

Data Index: 706008 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3589. Min Act: -0.0000

Data Index: 544173 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3603. Min Act: -0.0000

Data Index: 693828 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3471. Min Act: -0.0000

Data Index: 821126 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1152587 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3174. Min Act: -0.0000

Data Index: 885741 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1268215 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3393. Min Act: -0.0000

Data Index: 530601 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1241815 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3381. Min Act: -0.0000

Data Index: 143833 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1144386 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1136145 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3292. Min Act: -0.0000

Data Index: 172090 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3370. Min Act: -0.0000

Data Index: 311597 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.4540. Min Range: -0.4540

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1215544 (C4 (Web Text))

Max Activating Token Index: 522