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

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

Neuron 5492 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6766. Min Act: -0.0000

Data Index: 10784 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6093. Min Act: -0.0000

Data Index: 908304 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6066. Min Act: -0.0000

Data Index: 538019 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6829. Min Act: -0.0000

Data Index: 999790 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5805. Min Act: -0.0000

Data Index: 387689 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5558. Min Act: -0.0000

Data Index: 93257 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5631. Min Act: -0.0000

Data Index: 597915 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1124582 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1074594 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6201. Min Act: -0.0000

Data Index: 224554 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4924. Min Act: -0.0000

Data Index: 260604 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4882. Min Act: -0.0000

Data Index: 215526 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1278170 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4796. Min Act: -0.0000

Data Index: 743645 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4490. Min Act: -0.0000

Data Index: 119286 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4918. Min Act: -0.0000

Data Index: 453532 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1306690 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5290. Min Act: -0.0000

Data Index: 278384 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4627. Min Act: -0.0000

Data Index: 379732 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4156. Min Act: -0.0000

Data Index: 176219 (C4 (Web Text))

Max Activating Token Index: 331