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

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

Neuron 4589 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: 0.9921. Min Range: -0.9921

Max Act: 0.9921. Min Act: -0.0000

Data Index: 408629 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8746. Min Act: -0.0000

Data Index: 741093 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1358675 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8609. Min Act: -0.0000

Data Index: 672742 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1253454 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6602. Min Act: -0.0000

Data Index: 291976 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6776. Min Act: -0.0000

Data Index: 764714 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6711. Min Act: -0.0000

Data Index: 895171 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6145. Min Act: -0.0000

Data Index: 315566 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6656. Min Act: -0.0000

Data Index: 253773 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1131708 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5619. Min Act: -0.0000

Data Index: 108912 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1119399 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6081. Min Act: -0.0000

Data Index: 656118 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1199794 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1303977 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5744. Min Act: 0.0000

Data Index: 1058318 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5838. Min Act: -0.0000

Data Index: 634586 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5848. Min Act: -0.0000

Data Index: 343484 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5738. Min Act: 0.0000

Data Index: 1335311 (C4 (Web Text))

Max Activating Token Index: 352