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

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

Neuron 4060 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0780. Min Act: -0.0000

Data Index: 645622 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0706. Min Act: -0.0000

Data Index: 998257 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0616. Min Act: -0.0000

Data Index: 510745 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1222736 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0559. Min Act: -0.0000

Data Index: 865115 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0599. Min Act: -0.0000

Data Index: 610518 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0596. Min Act: -0.0000

Data Index: 522949 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0491. Min Act: -0.0000

Data Index: 904972 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0528. Min Act: -0.0000

Data Index: 461065 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0497. Min Act: -0.0000

Data Index: 644734 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1357589 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0497. Min Act: -0.0000

Data Index: 133627 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0458. Min Act: -0.0000

Data Index: 274883 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1291285 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0410. Min Act: -0.0000

Data Index: 955976 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0436. Min Act: -0.0000

Data Index: 203971 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1392600 (Python Code)

Max Activating Token Index: 286

Text #18

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0430. Min Act: -0.0000

Data Index: 797039 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0409. Min Act: -0.0000

Data Index: 693662 (C4 (Web Text))

Max Activating Token Index: 756