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

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

Neuron 3212 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: 0.2521. Min Range: -0.2521

Max Act: 0.2441. Min Act: -0.0000

Data Index: 461661 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2244. Min Act: -0.0000

Data Index: 635094 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2478. Min Act: -0.0000

Data Index: 790576 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2264. Min Act: -0.0000

Data Index: 765556 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2430. Min Act: -0.0000

Data Index: 620179 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1314120 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1204666 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2341. Min Act: -0.0000

Data Index: 317507 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2304. Min Act: -0.0000

Data Index: 63467 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2400. Min Act: -0.0000

Data Index: 414523 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2133. Min Act: -0.0000

Data Index: 734677 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2203. Min Act: -0.0000

Data Index: 859024 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1838. Min Act: -0.0000

Data Index: 453734 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1133501 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2244. Min Act: -0.0000

Data Index: 250637 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2209. Min Act: -0.0000

Data Index: 995821 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1106017 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2277. Min Act: -0.0000

Data Index: 336991 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2238. Min Act: -0.0000

Data Index: 107197 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2086. Min Act: -0.0000

Data Index: 765319 (C4 (Web Text))

Max Activating Token Index: 647