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

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

Neuron 3701 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7667. Min Act: -0.0001

Data Index: 333099 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7396. Min Act: -0.0001

Data Index: 381980 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7165. Min Act: -0.0001

Data Index: 207641 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6745. Min Act: -0.0001

Data Index: 189496 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6880. Min Act: -0.0001

Data Index: 1223549 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1237385 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6847. Min Act: -0.0001

Data Index: 327526 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6522. Min Act: -0.0001

Data Index: 1318455 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6678. Min Act: -0.0001

Data Index: 76824 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5851. Min Act: -0.0002

Data Index: 668089 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6877. Min Act: -0.0001

Data Index: 1016489 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6380. Min Act: -0.0001

Data Index: 838122 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6530. Min Act: -0.0001

Data Index: 393102 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6439. Min Act: -0.0001

Data Index: 1136886 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6804. Min Act: -0.0002

Data Index: 389112 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6007. Min Act: -0.0001

Data Index: 617883 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6128. Min Act: -0.0001

Data Index: 133804 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6484. Min Act: -0.0001

Data Index: 920140 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5864. Min Act: -0.0001

Data Index: 830688 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6281. Min Act: -0.0001

Data Index: 323510 (C4 (Web Text))

Max Activating Token Index: 696