Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 931 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1110783 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1153138 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1014432 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1201704 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6767. Min Act: -0.0000

Data Index: 44578 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6312. Min Act: -0.0000

Data Index: 213359 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6490. Min Act: -0.0000

Data Index: 593994 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6674. Min Act: -0.0000

Data Index: 683009 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6456. Min Act: -0.0000

Data Index: 271998 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6467. Min Act: -0.0000

Data Index: 262166 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6439. Min Act: -0.0000

Data Index: 9214 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1013972 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6448. Min Act: -0.0000

Data Index: 962605 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1277324 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6192. Min Act: -0.0000

Data Index: 519913 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6150. Min Act: -0.0000

Data Index: 781055 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6118. Min Act: -0.0000

Data Index: 885890 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6099. Min Act: -0.0000

Data Index: 129956 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5917. Min Act: -0.0000

Data Index: 842960 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6072. Min Act: -0.0000

Data Index: 501674 (C4 (Web Text))

Max Activating Token Index: 518