Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 260 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 1.0000. Min Range: -1.0000

Max Act: 1.0000. Min Act: -0.0003

Data Index: 3230 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8146. Min Act: -0.0004

Data Index: 280970 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8561. Min Act: -0.0004

Data Index: 876983 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7834. Min Act: -0.0003

Data Index: 1194733 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7794. Min Act: -0.0003

Data Index: 878032 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7015. Min Act: -0.0003

Data Index: 297889 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7343. Min Act: -0.0003

Data Index: 1333779 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7326. Min Act: -0.0003

Data Index: 1018680 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6820. Min Act: -0.0003

Data Index: 58782 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7219. Min Act: -0.0003

Data Index: 1167622 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7054. Min Act: -0.0003

Data Index: 619943 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6639. Min Act: -0.0003

Data Index: 765888 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6925. Min Act: -0.0003

Data Index: 303617 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7014. Min Act: -0.0003

Data Index: 613901 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6972. Min Act: -0.0003

Data Index: 771543 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6870. Min Act: -0.0003

Data Index: 980683 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7293. Min Act: -0.0003

Data Index: 469631 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6865. Min Act: -0.0003

Data Index: 1155020 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6706. Min Act: -0.0003

Data Index: 662727 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6584. Min Act: -0.0003

Data Index: 760769 (C4 (Web Text))

Max Activating Token Index: 181