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

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

Neuron 1200 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1800. Min Act: -0.0002

Data Index: 1106823 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1364. Min Act: -0.0002

Data Index: 1173877 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1306. Min Act: -0.0002

Data Index: 914293 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1212. Min Act: -0.0002

Data Index: 658773 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1105. Min Act: -0.0002

Data Index: 671540 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1133. Min Act: -0.0002

Data Index: 251025 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1124. Min Act: -0.0002

Data Index: 576594 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1110. Min Act: -0.0002

Data Index: 912953 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1137. Min Act: -0.0002

Data Index: 719668 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1053. Min Act: -0.0002

Data Index: 421301 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1045. Min Act: -0.0002

Data Index: 405524 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1216681 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1021. Min Act: -0.0002

Data Index: 70604 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1217919 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1060. Min Act: -0.0002

Data Index: 109043 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1013. Min Act: -0.0002

Data Index: 193607 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1207295 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0988. Min Act: -0.0002

Data Index: 56787 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0992. Min Act: -0.0002

Data Index: 333094 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.0985. Min Act: -0.0002

Data Index: 18420 (C4 (Web Text))

Max Activating Token Index: 127