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

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

Neuron 1178 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.8663. Min Act: -0.0000

Data Index: 822873 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.8104. Min Act: -0.0000

Data Index: 116798 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7426. Min Act: -0.0000

Data Index: 469753 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1491941 (Python Code)

Max Activating Token Index: 29

Text #4

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7652. Min Act: -0.0000

Data Index: 777296 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7507. Min Act: -0.0000

Data Index: 724425 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7225. Min Act: -0.0000

Data Index: 523112 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7289. Min Act: -0.0000

Data Index: 241712 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1192196 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1357319 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1007395 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7078. Min Act: -0.0001

Data Index: 1222259 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6361. Min Act: -0.0000

Data Index: 357565 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6996. Min Act: -0.0000

Data Index: 891798 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6760. Min Act: -0.0000

Data Index: 579079 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6356. Min Act: -0.0000

Data Index: 555889 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6867. Min Act: -0.0000

Data Index: 615856 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6643. Min Act: -0.0001

Data Index: 1222279 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1317870 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6447. Min Act: -0.0000

Data Index: 525921 (C4 (Web Text))

Max Activating Token Index: 526