Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 689 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1233. Min Act: -0.0002

Data Index: 283164 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1291547 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1202. Min Act: -0.0002

Data Index: 696471 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1157. Min Act: -0.0002

Data Index: 104445 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1145. Min Act: -0.0001

Data Index: 622686 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1164350 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1010518 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1060. Min Act: -0.0002

Data Index: 118331 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1080. Min Act: -0.0002

Data Index: 661845 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1057. Min Act: -0.0002

Data Index: 330011 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1079. Min Act: -0.0002

Data Index: 264896 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1163427 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1027. Min Act: -0.0002

Data Index: 242719 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1000. Min Act: -0.0002

Data Index: 729287 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1017. Min Act: -0.0001

Data Index: 397475 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0995. Min Act: -0.0002

Data Index: 546695 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0958. Min Act: -0.0002

Data Index: 150670 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0959. Min Act: -0.0002

Data Index: 355484 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0976. Min Act: -0.0001

Data Index: 28944 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0955. Min Act: -0.0002

Data Index: 345330 (C4 (Web Text))

Max Activating Token Index: 384