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

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

Neuron 4176 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.2296. Min Act: -0.0000

Data Index: 357180 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1475269 (Python Code)

Max Activating Token Index: 320

Text #2

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.2210. Min Act: -0.0000

Data Index: 716880 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1123647 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.2449. Min Act: -0.0000

Data Index: 1461011 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.0991. Min Act: -0.0000

Data Index: 18890 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1651236 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1382350 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1549000 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.0499. Min Act: -0.0000

Data Index: 480097 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1646838 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.0119. Min Act: -0.0000

Data Index: 1131827 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.9644. Min Act: -0.0000

Data Index: 208601 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 1.2449. Min Range: -1.2449

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1349927 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.9437. Min Act: -0.0000

Data Index: 740195 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1624789 (Python Code)

Max Activating Token Index: 290

Text #16

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8535. Min Act: -0.0000

Data Index: 339306 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1580067 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8783. Min Act: -0.0000

Data Index: 77378 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.2449. Min Range: -1.2449

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1532907 (Python Code)

Max Activating Token Index: 881