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

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

Neuron 1370 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.7269. Min Act: -0.0002

Data Index: 123542 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.7200. Min Act: -0.0002

Data Index: 650168 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.7196. Min Act: -0.0002

Data Index: 58351 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.7182. Min Act: -0.0002

Data Index: 1188903 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.7190. Min Act: -0.0002

Data Index: 969315 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.7108. Min Act: -0.0002

Data Index: 1030434 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.7032. Min Act: -0.0002

Data Index: 277470 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.6383. Min Act: -0.0002

Data Index: 171455 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.6355. Min Act: -0.0002

Data Index: 483890 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.6259. Min Act: -0.0001

Data Index: 1192439 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.6079. Min Act: -0.0002

Data Index: 57194 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.6045. Min Act: -0.0002

Data Index: 888391 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.5992. Min Act: -0.0002

Data Index: 658423 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.5931. Min Act: -0.0002

Data Index: 512578 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.5865. Min Act: -0.0002

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.5867. Min Act: -0.0002

Data Index: 498789 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.5858. Min Act: -0.0002

Data Index: 531263 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.5826. Min Act: -0.0002

Data Index: 84308 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.5738. Min Act: -0.0001

Data Index: 974813 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 1.7269. Min Range: -1.7269

Max Act: 1.5743. Min Act: -0.0002

Data Index: 662764 (C4 (Web Text))

Max Activating Token Index: 684