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

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

Neuron 4531 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.8231. Min Act: -0.0000

Data Index: 121605 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7854. Min Act: 0.0000

Data Index: 596464 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1142246 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6978. Min Act: -0.0000

Data Index: 234490 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6416. Min Act: -0.0000

Data Index: 353969 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6029. Min Act: -0.0000

Data Index: 400106 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6690. Min Act: -0.0000

Data Index: 35907 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6164. Min Act: -0.0000

Data Index: 276743 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6130. Min Act: -0.0000

Data Index: 827739 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1116348 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5949. Min Act: -0.0000

Data Index: 921456 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5956. Min Act: -0.0000

Data Index: 762892 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5915. Min Act: -0.0000

Data Index: 669727 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1308975 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5969. Min Act: -0.0000

Data Index: 210839 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5670. Min Act: -0.0000

Data Index: 981974 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5851. Min Act: -0.0000

Data Index: 375255 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5797. Min Act: -0.0000

Data Index: 702075 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5808. Min Act: 0.0000

Data Index: 461015 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.8231. Min Range: -0.8231

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1352753 (C4 (Web Text))

Max Activating Token Index: 122