Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3563 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.9152. Min Act: -0.0001

Data Index: 1126047 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.8957. Min Act: -0.0001

Data Index: 688270 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7974. Min Act: -0.0000

Data Index: 443574 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7628. Min Act: -0.0001

Data Index: 1012187 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7295. Min Act: -0.0001

Data Index: 748373 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7622. Min Act: -0.0001

Data Index: 840486 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6874. Min Act: -0.0001

Data Index: 850177 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6902. Min Act: -0.0000

Data Index: 760187 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6364. Min Act: -0.0001

Data Index: 5049 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6731. Min Act: -0.0001

Data Index: 500270 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6669. Min Act: -0.0001

Data Index: 13728 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5810. Min Act: -0.0001

Data Index: 643859 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5992. Min Act: -0.0000

Data Index: 987404 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6420. Min Act: -0.0001

Data Index: 656585 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6213. Min Act: -0.0001

Data Index: 545383 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5687. Min Act: -0.0000

Data Index: 701110 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5998. Min Act: -0.0001

Data Index: 44918 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5814. Min Act: -0.0001

Data Index: 326222 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6159. Min Act: -0.0001

Data Index: 1121815 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5771. Min Act: -0.0001

Data Index: 478126 (C4 (Web Text))

Max Activating Token Index: 960