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

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

Neuron 1980 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3836. Min Range: -2.3836

Max Act: 2.3836. Min Act: -0.0000

Data Index: 368550 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.9119. Min Act: -0.0000

Data Index: 874199 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.5365. Min Act: -0.0000

Data Index: 579124 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1176187 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.2598. Min Act: -0.0000

Data Index: 312205 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.1449. Min Act: -0.0000

Data Index: 762370 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1597810 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.1942. Min Act: -0.0000

Data Index: 665514 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.1092. Min Act: -0.0000

Data Index: 477365 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1257967 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.1074. Min Act: -0.0000

Data Index: 1144193 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.0592. Min Act: -0.0001

Data Index: 1204062 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.0988. Min Act: -0.0000

Data Index: 21566 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1233756 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1276717 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.1171. Min Act: -0.0000

Data Index: 948860 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 2.3836. Min Range: -2.3836

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1199665 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 2.3836. Min Range: -2.3836

Max Act: 1.0002. Min Act: -0.0000

Data Index: 617067 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 2.3836. Min Range: -2.3836

Max Act: 0.9848. Min Act: -0.0001

Data Index: 592533 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 2.3836. Min Range: -2.3836

Max Act: 0.9354. Min Act: -0.0000

Data Index: 694215 (C4 (Web Text))

Max Activating Token Index: 886