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

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

Neuron 3149 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: 1.3556. Min Range: -1.3556

Max Act: 1.3556. Min Act: -0.0000

Data Index: 676320 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2500. Min Act: -0.0000

Data Index: 960113 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2182. Min Act: -0.0000

Data Index: 673463 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.3375. Min Act: -0.0000

Data Index: 691656 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2288. Min Act: -0.0000

Data Index: 666298 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2193. Min Act: -0.0000

Data Index: 808805 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2220. Min Act: -0.0000

Data Index: 485675 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2075. Min Act: -0.0000

Data Index: 73644 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1912. Min Act: -0.0000

Data Index: 397049 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2441. Min Act: -0.0000

Data Index: 399873 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0809. Min Act: -0.0000

Data Index: 61967 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0211. Min Act: -0.0000

Data Index: 907550 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.2152. Min Act: -0.0000

Data Index: 657934 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1228. Min Act: -0.0000

Data Index: 896715 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1320101 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.1657. Min Act: -0.0000

Data Index: 143664 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0901. Min Act: -0.0000

Data Index: 823380 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0246. Min Act: -0.0000

Data Index: 618928 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0789. Min Act: -0.0000

Data Index: 88762 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.3556. Min Range: -1.3556

Max Act: 1.0692. Min Act: -0.0000

Data Index: 319834 (C4 (Web Text))

Max Activating Token Index: 764