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

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

Neuron 3370 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1268263 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1219105 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0785. Min Act: -0.0000

Data Index: 450027 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0788. Min Act: -0.0001

Data Index: 382722 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0836. Min Act: -0.0001

Data Index: 734701 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0766. Min Act: -0.0000

Data Index: 363126 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0765. Min Act: -0.0000

Data Index: 563600 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0675. Min Act: -0.0000

Data Index: 382225 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0743. Min Act: -0.0001

Data Index: 701833 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0805. Min Act: -0.0000

Data Index: 656798 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0798. Min Act: -0.0000

Data Index: 847297 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0734. Min Act: -0.0001

Data Index: 348089 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0744. Min Act: -0.0000

Data Index: 258750 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0721. Min Act: -0.0000

Data Index: 129641 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1084386 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0752. Min Act: -0.0000

Data Index: 16051 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0721. Min Act: -0.0001

Data Index: 481014 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0695. Min Act: -0.0000

Data Index: 390680 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1193656 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1237891 (C4 (Web Text))

Max Activating Token Index: 525