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

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

Neuron 2200 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.5988. Min Act: -0.0000

Data Index: 932237 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.5628. Min Act: -0.0000

Data Index: 376760 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.4999. Min Act: -0.0000

Data Index: 138401 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.4148. Min Act: -0.0000

Data Index: 448951 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3264. Min Act: -0.0000

Data Index: 416600 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.4073. Min Act: -0.0000

Data Index: 747289 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2931. Min Act: -0.0000

Data Index: 572718 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3587. Min Act: -0.0000

Data Index: 259779 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3317. Min Act: -0.0000

Data Index: 676197 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3304. Min Act: -0.0000

Data Index: 322120 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3296. Min Act: -0.0000

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3285. Min Act: -0.0000

Data Index: 180091 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1179313 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2850. Min Act: -0.0000

Data Index: 149740 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.1960. Min Act: -0.0000

Data Index: 377617 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2637. Min Act: -0.0000

Data Index: 1270412 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2650. Min Act: -0.0000

Data Index: 268764 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2420. Min Act: -0.0000

Data Index: 27005 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.1926. Min Act: -0.0000

Data Index: 658269 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2946. Min Act: -0.0000

Data Index: 1310530 (C4 (Web Text))

Max Activating Token Index: 704