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

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

Neuron 1726 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.6496. Min Act: -0.0001

Data Index: 681956 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.5562. Min Act: -0.0001

Data Index: 1161795 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.5389. Min Act: -0.0001

Data Index: 987988 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.5093. Min Act: -0.0001

Data Index: 1329598 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.5637. Min Act: -0.0001

Data Index: 278527 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4967. Min Act: -0.0001

Data Index: 1304427 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.5432. Min Act: -0.0001

Data Index: 734708 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.5232. Min Act: -0.0001

Data Index: 917670 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4567. Min Act: -0.0001

Data Index: 765717 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.5248. Min Act: -0.0001

Data Index: 584818 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4849. Min Act: -0.0001

Data Index: 12501 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4891. Min Act: -0.0001

Data Index: 325969 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.5163. Min Act: -0.0001

Data Index: 1235484 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4584. Min Act: -0.0001

Data Index: 1192576 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4732. Min Act: -0.0001

Data Index: 1142958 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4508. Min Act: -0.0001

Data Index: 942526 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4473. Min Act: -0.0001

Data Index: 1150906 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4624. Min Act: -0.0001

Data Index: 589904 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.4758. Min Act: -0.0001

Data Index: 339611 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.6496. Min Range: -0.6496

Max Act: 0.5000. Min Act: -0.0001

Data Index: 94658 (C4 (Web Text))

Max Activating Token Index: 858