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

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

Neuron 622 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1281. Min Act: -0.0002

Data Index: 581039 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1010497 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1220. Min Act: -0.0002

Data Index: 742723 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1210. Min Act: -0.0002

Data Index: 1227459 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1257. Min Act: -0.0002

Data Index: 483252 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1181. Min Act: -0.0002

Data Index: 773799 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1128823 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1023062 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1248. Min Act: -0.0002

Data Index: 988044 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1020. Min Act: -0.0002

Data Index: 1026102 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1087. Min Act: -0.0002

Data Index: 665246 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1330820 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0898. Min Act: -0.0002

Data Index: 466442 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1063693 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1046. Min Act: -0.0002

Data Index: 588770 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1106282 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1015672 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1036. Min Act: -0.0002

Data Index: 613204 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1105. Min Act: -0.0002

Data Index: 961573 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1043840 (C4 (Web Text))

Max Activating Token Index: 685