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

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

Neuron 2893 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8017. Min Act: -0.0000

Data Index: 529928 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1358758 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8486. Min Act: -0.0000

Data Index: 735219 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1255545 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.6630. Min Act: -0.0000

Data Index: 982809 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.6473. Min Act: -0.0000

Data Index: 1208472 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5905. Min Act: -0.0000

Data Index: 1160493 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5754. Min Act: -0.0000

Data Index: 1278078 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7026. Min Act: -0.0000

Data Index: 506620 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5583. Min Act: -0.0000

Data Index: 91114 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.6042. Min Act: -0.0000

Data Index: 836280 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5947. Min Act: -0.0000

Data Index: 1144810 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5891. Min Act: -0.0000

Data Index: 477299 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5819. Min Act: -0.0000

Data Index: 936935 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5400. Min Act: -0.0000

Data Index: 35343 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5342. Min Act: -0.0000

Data Index: 388458 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.6159. Min Act: -0.0000

Data Index: 582133 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.6147. Min Act: -0.0000

Data Index: 426730 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1037531 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5047. Min Act: -0.0000

Data Index: 673038 (C4 (Web Text))

Max Activating Token Index: 823