Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2713 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.8688. Min Act: 0.0000

Data Index: 1199869 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7093. Min Act: 0.0000

Data Index: 664803 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6687. Min Act: 0.0000

Data Index: 1294935 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6706. Min Act: -0.0000

Data Index: 197906 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6134. Min Act: -0.0000

Data Index: 32742 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6119. Min Act: -0.0000

Data Index: 561956 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5894. Min Act: -0.0000

Data Index: 185499 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6033. Min Act: -0.0001

Data Index: 745289 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6054. Min Act: -0.0001

Data Index: 1159903 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6239. Min Act: -0.0001

Data Index: 607651 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1012674 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5817. Min Act: -0.0001

Data Index: 150527 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5928. Min Act: -0.0000

Data Index: 719023 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5906. Min Act: -0.0000

Data Index: 857347 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5707. Min Act: -0.0000

Data Index: 744107 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5848. Min Act: 0.0000

Data Index: 1197560 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5859. Min Act: -0.0000

Data Index: 107813 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5806. Min Act: 0.0000

Data Index: 513141 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5930. Min Act: -0.0000

Data Index: 605304 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5526. Min Act: -0.0000

Data Index: 103013 (C4 (Web Text))

Max Activating Token Index: 966