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

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

Neuron 3504 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7961. Min Act: -0.0000

Data Index: 283732 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.8106. Min Act: -0.0000

Data Index: 731236 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.8168. Min Act: -0.0000

Data Index: 216173 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7060. Min Act: -0.0000

Data Index: 598687 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6939. Min Act: -0.0000

Data Index: 26381 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7367. Min Act: -0.0000

Data Index: 910609 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6793. Min Act: -0.0000

Data Index: 34359 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6092. Min Act: -0.0000

Data Index: 99060 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6593. Min Act: 0.0000

Data Index: 1326039 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6621. Min Act: -0.0000

Data Index: 830455 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6598. Min Act: -0.0000

Data Index: 715516 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6563. Min Act: -0.0000

Data Index: 871707 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6573. Min Act: -0.0000

Data Index: 126754 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1107978 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6416. Min Act: -0.0000

Data Index: 722214 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6214. Min Act: -0.0000

Data Index: 4272 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5835. Min Act: -0.0000

Data Index: 533423 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5995. Min Act: -0.0000

Data Index: 687195 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6084. Min Act: -0.0000

Data Index: 312873 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5878. Min Act: -0.0000

Data Index: 562999 (C4 (Web Text))

Max Activating Token Index: 193