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

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

Neuron 3384 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: 0.2737. Min Range: -0.2737

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1013202 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2440. Min Act: -0.0000

Data Index: 672336 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1210057 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2329. Min Act: -0.0000

Data Index: 639925 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2345. Min Act: -0.0000

Data Index: 215803 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2262. Min Act: -0.0000

Data Index: 470180 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1267064 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2210. Min Act: -0.0000

Data Index: 586469 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2195. Min Act: -0.0000

Data Index: 660994 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2104. Min Act: -0.0000

Data Index: 471247 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2171. Min Act: -0.0000

Data Index: 499682 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2178. Min Act: -0.0000

Data Index: 647670 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2078. Min Act: -0.0000

Data Index: 13198 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1340054 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2090. Min Act: -0.0000

Data Index: 599787 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1993. Min Act: -0.0000

Data Index: 541845 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2004. Min Act: -0.0000

Data Index: 348198 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1352431 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1184404 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1896. Min Act: -0.0000

Data Index: 42239 (C4 (Web Text))

Max Activating Token Index: 485