Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 875 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2175. Min Act: -0.0000

Data Index: 532386 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2160. Min Act: -0.0000

Data Index: 182115 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1194759 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1802. Min Act: -0.0000

Data Index: 259408 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1777. Min Act: -0.0000

Data Index: 965457 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1792. Min Act: -0.0000

Data Index: 105113 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1706. Min Act: -0.0000

Data Index: 896694 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1721. Min Act: -0.0000

Data Index: 550083 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1763. Min Act: -0.0000

Data Index: 280458 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1677. Min Act: -0.0000

Data Index: 838679 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1687. Min Act: -0.0000

Data Index: 724600 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1012851 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1129139 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1778. Min Act: -0.0000

Data Index: 457364 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1693. Min Act: -0.0000

Data Index: 119270 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1691. Min Act: -0.0000

Data Index: 902733 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1653. Min Act: -0.0000

Data Index: 310654 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1661. Min Act: -0.0000

Data Index: 612004 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1659. Min Act: -0.0000

Data Index: 624388 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.2175. Min Range: -0.2175

Max Act: 0.1736. Min Act: -0.0000

Data Index: 14152 (C4 (Web Text))

Max Activating Token Index: 729